Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.3100. Min Act: -0.1700
Data Index: 4353911 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.2163. Min Act: -0.1700
Data Index: 2081680 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0913. Min Act: -0.1700
Data Index: 1693938 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0600. Min Act: -0.1700
Data Index: 2285644 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0913. Min Act: -0.1700
Data Index: 1548181 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0600. Min Act: -0.1700
Data Index: 1062899 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0288. Min Act: -0.1700
Data Index: 6828717 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.9350. Min Act: -0.1700
Data Index: 2782210 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.9038. Min Act: -0.1700
Data Index: 5433634 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.9038. Min Act: -0.1700
Data Index: 7084298 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8725. Min Act: -0.1700
Data Index: 6141929 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8413. Min Act: -0.1700
Data Index: 2687975 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8725. Min Act: -0.1700
Data Index: 1313808 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 367909 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 5208222 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8413. Min Act: -0.1700
Data Index: 5036341 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 4430410 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7788. Min Act: -0.1700
Data Index: 3101211 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 6085455 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 3034669 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19