Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.3153. Min Act: -0.1700
Data Index: 5278086 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0653. Min Act: -0.1700
Data Index: 192418 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0966. Min Act: -0.1700
Data Index: 516489 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0341. Min Act: -0.1700
Data Index: 8348169 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0341. Min Act: -0.1700
Data Index: 2975485 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0341. Min Act: -0.1700
Data Index: 810603 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.9716. Min Act: -0.1700
Data Index: 2204595 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.9091. Min Act: -0.1700
Data Index: 2975472 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8778. Min Act: -0.1700
Data Index: 6535084 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8466. Min Act: -0.1700
Data Index: 5409142 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8466. Min Act: -0.1700
Data Index: 1887345 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7841. Min Act: -0.1700
Data Index: 1870118 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8153. Min Act: -0.1700
Data Index: 6842487 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8153. Min Act: -0.1700
Data Index: 2677546 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7841. Min Act: -0.1700
Data Index: 2135356 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7528. Min Act: -0.1700
Data Index: 4832253 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7841. Min Act: -0.1700
Data Index: 1873302 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 4857330 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7528. Min Act: -0.1700
Data Index: 5958629 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7528. Min Act: -0.1700
Data Index: 149656 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19