Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.6488. Min Act: -0.1700
Data Index: 2884673 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.6176. Min Act: -0.1700
Data Index: 5579630 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.4926. Min Act: -0.1700
Data Index: 1633665 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.4301. Min Act: -0.1700
Data Index: 7249102 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.4301. Min Act: -0.1700
Data Index: 3856747 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3676. Min Act: -0.1700
Data Index: 7492251 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3676. Min Act: -0.1700
Data Index: 7532586 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3363. Min Act: -0.1700
Data Index: 2779099 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3363. Min Act: -0.1700
Data Index: 8609776 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3363. Min Act: -0.1700
Data Index: 2965564 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3051. Min Act: -0.1700
Data Index: 2736325 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2738. Min Act: -0.1700
Data Index: 2315910 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3051. Min Act: -0.1700
Data Index: 6421154 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.3051. Min Act: -0.1700
Data Index: 7410139 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2426. Min Act: -0.1700
Data Index: 3566135 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2426. Min Act: -0.1700
Data Index: 8031439 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2738. Min Act: -0.1700
Data Index: 4369363 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2426. Min Act: -0.1700
Data Index: 872753 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2426. Min Act: -0.1700
Data Index: 6743356 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6488. Min Range: -5.6488
Max Act: 5.2426. Min Act: -0.1700
Data Index: 652792 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19