Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.8192. Min Act: -0.1700
Data Index: 6954206 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.7254. Min Act: -0.1700
Data Index: 6389216 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6942. Min Act: -0.1700
Data Index: 4110462 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6942. Min Act: -0.1700
Data Index: 2907757 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6629. Min Act: -0.1700
Data Index: 3133774 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6317. Min Act: -0.1700
Data Index: 849798 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6317. Min Act: -0.1700
Data Index: 6098622 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6317. Min Act: -0.1700
Data Index: 3295350 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6317. Min Act: -0.1700
Data Index: 7755159 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6004. Min Act: -0.1700
Data Index: 8228046 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.6004. Min Act: -0.1700
Data Index: 1972536 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5692. Min Act: -0.1700
Data Index: 5073935 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5692. Min Act: -0.1700
Data Index: 3251801 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5692. Min Act: -0.1700
Data Index: 824221 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5379. Min Act: -0.1700
Data Index: 2154538 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5379. Min Act: -0.1700
Data Index: 7622385 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5067. Min Act: -0.1700
Data Index: 2088425 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5067. Min Act: -0.1700
Data Index: 120365 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5067. Min Act: -0.1700
Data Index: 5672064 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8192. Min Range: -5.8192
Max Act: 5.5067. Min Act: -0.1700
Data Index: 607875 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19