Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.9506. Min Act: -0.1700
Data Index: 3432381 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.9506. Min Act: -0.1700
Data Index: 6823634 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.7006. Min Act: -0.1700
Data Index: 3250151 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.7006. Min Act: -0.1700
Data Index: 8576896 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.5131. Min Act: -0.1700
Data Index: 4022750 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.5131. Min Act: -0.1700
Data Index: 2203215 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.5131. Min Act: -0.1700
Data Index: 4305234 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.4506. Min Act: -0.1700
Data Index: 6120207 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.4506. Min Act: -0.1700
Data Index: 8161096 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.4506. Min Act: -0.1700
Data Index: 6372385 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3881. Min Act: -0.1700
Data Index: 2210644 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 8005977 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 1645359 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 5377958 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 6946787 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 6483912 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 3896748 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.3256. Min Act: -0.1700
Data Index: 8564014 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.2631. Min Act: -0.1700
Data Index: 2300999 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9506. Min Range: -10.9506
Max Act: 10.2631. Min Act: -0.1700
Data Index: 4892454 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19