Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.6100. Min Act: -0.1700
Data Index: 6653360 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5943. Min Act: -0.1700
Data Index: 637072 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5786. Min Act: -0.1700
Data Index: 6653350 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5708. Min Act: -0.1700
Data Index: 2590945 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5786. Min Act: -0.1699
Data Index: 3948854 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5708. Min Act: -0.1700
Data Index: 2764488 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5708. Min Act: -0.1698
Data Index: 233505 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5631. Min Act: -0.1700
Data Index: 2764494 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5631. Min Act: -0.1700
Data Index: 3179868 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5553. Min Act: -0.1700
Data Index: 6448635 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5553. Min Act: -0.1700
Data Index: 1944091 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5553. Min Act: -0.1700
Data Index: 5867710 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5476. Min Act: -0.1698
Data Index: 7312058 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5400. Min Act: -0.1700
Data Index: 6653356 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5476. Min Act: -0.1700
Data Index: 2448611 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5476. Min Act: -0.1700
Data Index: 3944023 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5553. Min Act: -0.1700
Data Index: 233500 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5553. Min Act: -0.1700
Data Index: 233504 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5400. Min Act: -0.1700
Data Index: 5526159 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6100. Min Range: -0.6100
Max Act: 0.5476. Min Act: -0.1699
Data Index: 3516432 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19