Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 5419317 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.3474. Min Act: -0.1700
Data Index: 6378212 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 4531979 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2849. Min Act: -0.1700
Data Index: 1804035 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 309162 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 2430037 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 4722697 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 1400948 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 8699461 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 6048834 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.0974. Min Act: -0.1700
Data Index: 4908092 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 5386803 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 8703223 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.0974. Min Act: -0.1700
Data Index: 4978670 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.2224. Min Act: -0.1700
Data Index: 5189799 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 5657833 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 3772869 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.0974. Min Act: -0.1700
Data Index: 7692507 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 5430487 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4099. Min Range: -9.4099
Max Act: 9.1599. Min Act: -0.1700
Data Index: 975059 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19