Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.5419. Min Act: -0.1700
Data Index: 3104881 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.4794. Min Act: -0.1700
Data Index: 5766363 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.4169. Min Act: -0.1700
Data Index: 4357211 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.2294. Min Act: -0.1700
Data Index: 1493195 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.1669. Min Act: -0.1700
Data Index: 2502380 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.1669. Min Act: -0.1700
Data Index: 6529663 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.1044. Min Act: -0.1700
Data Index: 4263627 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.1044. Min Act: -0.1700
Data Index: 1643124 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.0419. Min Act: -0.1700
Data Index: 7323951 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.1044. Min Act: -0.1700
Data Index: 8015284 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5419. Min Range: -10.5419
Max Act: 10.0419. Min Act: -0.1700
Data Index: 5841584 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9794. Min Act: -0.1700
Data Index: 6965104 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9794. Min Act: -0.1700
Data Index: 5778987 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1700
Data Index: 3311115 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1700
Data Index: 971905 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1700
Data Index: 4573393 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.8544. Min Act: -0.1700
Data Index: 1454562 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1700
Data Index: 4807968 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1700
Data Index: 869187 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5419. Min Range: -10.5419
Max Act: 9.9169. Min Act: -0.1699
Data Index: 4766612 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19