Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9979. Min Act: -0.1700
Data Index: 5497490 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0291. Min Range: -4.0291
Max Act: 4.0291. Min Act: -0.1700
Data Index: 2529727 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9666. Min Act: -0.1700
Data Index: 8516964 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9666. Min Act: -0.1700
Data Index: 7528514 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9353. Min Act: -0.1700
Data Index: 399198 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9353. Min Act: -0.1700
Data Index: 6416622 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9353. Min Act: -0.1700
Data Index: 1918148 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9353. Min Act: -0.1700
Data Index: 5899821 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1459498 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9041. Min Act: -0.1700
Data Index: 3528792 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9041. Min Act: -0.1700
Data Index: 6208415 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 1489406 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 868586 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 5818724 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 5682218 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 6719222 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 4742977 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9041. Min Act: -0.1700
Data Index: 319828 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 2206888 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8728. Min Act: -0.1700
Data Index: 1485147 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19