Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.6529. Min Act: -0.1700
Data Index: 5392415 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.5725. Min Act: -0.1700
Data Index: 5920289 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.5240. Min Act: -0.1700
Data Index: 382755 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4592. Min Act: -0.1700
Data Index: 1103942 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4754. Min Act: -0.1700
Data Index: 52280 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4754. Min Act: -0.1700
Data Index: 4089872 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4592. Min Act: -0.1700
Data Index: 4558942 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4592. Min Act: -0.1700
Data Index: 2496552 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4429. Min Act: -0.1700
Data Index: 8783518 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4592. Min Act: -0.1700
Data Index: 5072333 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4429. Min Act: -0.1700
Data Index: 1830183 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4266. Min Act: -0.1700
Data Index: 1395516 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4103. Min Act: -0.1700
Data Index: 176460 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.3940. Min Act: -0.1700
Data Index: 4345589 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.3940. Min Act: -0.1700
Data Index: 461875 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.3940. Min Act: -0.1700
Data Index: 121866 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4103. Min Act: -0.1700
Data Index: 4464400 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.4103. Min Act: -0.1700
Data Index: 4766606 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.3449. Min Act: -0.1700
Data Index: 428049 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6529. Min Range: -2.6529
Max Act: 2.3449. Min Act: -0.1700
Data Index: 3025723 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19