Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2262 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.5202. Min Act: -0.1700
Data Index: 8400400 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.4419. Min Act: -0.1700
Data Index: 1922 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.4262. Min Act: -0.1700
Data Index: 4696872 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.4105. Min Act: -0.1700
Data Index: 5338522 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.4105. Min Act: -0.1700
Data Index: 6857123 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3948. Min Act: -0.1700
Data Index: 2545899 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3948. Min Act: -0.1700
Data Index: 4278603 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3791. Min Act: -0.1700
Data Index: 5535358 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3478. Min Act: -0.1700
Data Index: 179800 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3635. Min Act: -0.1700
Data Index: 8669690 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3635. Min Act: -0.1700
Data Index: 7189701 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3478. Min Act: -0.1700
Data Index: 7317011 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3791. Min Act: -0.1700
Data Index: 7602011 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3635. Min Act: -0.1700
Data Index: 1745652 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3321. Min Act: -0.1700
Data Index: 8270997 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3321. Min Act: -0.1700
Data Index: 7336176 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3478. Min Act: -0.1700
Data Index: 4509776 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3164. Min Act: -0.1700
Data Index: 8606345 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3164. Min Act: -0.1700
Data Index: 7686900 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3164. Min Act: -0.1700
Data Index: 2807471 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19