Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 510 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.3459. Min Act: -0.1700
Data Index: 5455624 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.3459. Min Act: -0.1700
Data Index: 3298289 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.3146. Min Act: -0.1700
Data Index: 630966 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.3146. Min Act: -0.1700
Data Index: 5016265 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2834. Min Act: -0.1700
Data Index: 4546627 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2834. Min Act: -0.1700
Data Index: 2621338 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.3146. Min Act: -0.1700
Data Index: 4501498 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2834. Min Act: -0.1700
Data Index: 7673173 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 8184014 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 2258234 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2209. Min Act: -0.1700
Data Index: 239799 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 4599653 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 5541623 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2834. Min Act: -0.1700
Data Index: 2677449 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 3190146 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2521. Min Act: -0.1700
Data Index: 5280504 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2941460 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.1896. Min Act: -0.1700
Data Index: 3577639 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2209. Min Act: -0.1700
Data Index: 5122678 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3459. Min Range: -5.3459
Max Act: 5.2209. Min Act: -0.1700
Data Index: 7919655 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19