Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.7296. Min Act: -0.1700
Data Index: 3829370 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6655. Min Act: -0.1700
Data Index: 8121466 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6495. Min Act: -0.1700
Data Index: 8121468 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6174. Min Act: -0.1700
Data Index: 7693255 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6334. Min Act: -0.1700
Data Index: 4569348 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6174. Min Act: -0.1700
Data Index: 6831382 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6334. Min Act: -0.1699
Data Index: 8636721 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6334. Min Act: -0.1700
Data Index: 4616497 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6174. Min Act: -0.1700
Data Index: 6831386 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6334. Min Act: -0.1700
Data Index: 2310874 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6174. Min Act: -0.1700
Data Index: 6831384 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6013. Min Act: -0.1700
Data Index: 6935921 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.6013. Min Act: -0.1700
Data Index: 6831383 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5852. Min Act: -0.1700
Data Index: 8421078 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5206. Min Act: -0.1699
Data Index: 2289078 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5691. Min Act: -0.1700
Data Index: 3297105 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5368. Min Act: -0.1700
Data Index: 1984840 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5368. Min Act: -0.1700
Data Index: 2900094 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5368. Min Act: -0.1700
Data Index: 38946 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7296. Min Range: -2.7296
Max Act: 2.5044. Min Act: -0.1700
Data Index: 6463834 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19