Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4274 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.7252. Min Act: -0.1700
Data Index: 3455703 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.6157. Min Act: -0.1700
Data Index: 4039665 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.6157. Min Act: -0.1700
Data Index: 6279060 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.6157. Min Act: -0.1700
Data Index: 1712565 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.5218. Min Act: -0.1700
Data Index: 2442794 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.5218. Min Act: -0.1700
Data Index: 7225472 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.5061. Min Act: -0.1700
Data Index: 4197221 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4905. Min Act: -0.1700
Data Index: 5795942 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4905. Min Act: -0.1700
Data Index: 4610208 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4748. Min Act: -0.1700
Data Index: 5657215 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4905. Min Act: -0.1700
Data Index: 8141145 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4591. Min Act: -0.1700
Data Index: 885572 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4591. Min Act: -0.1700
Data Index: 3712836 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4591. Min Act: -0.1700
Data Index: 571387 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4591. Min Act: -0.1700
Data Index: 5581942 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4591. Min Act: -0.1700
Data Index: 4403152 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4434. Min Act: -0.1700
Data Index: 189367 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4434. Min Act: -0.1700
Data Index: 8069856 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4278. Min Act: -0.1700
Data Index: 4865277 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7252. Min Range: -3.7252
Max Act: 3.4278. Min Act: -0.1700
Data Index: 4725886 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19