Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.9471. Min Act: -0.1700
Data Index: 4321913 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.9471. Min Act: -0.1700
Data Index: 7390380 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.9159. Min Act: -0.1700
Data Index: 6204452 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.8846. Min Act: -0.1700
Data Index: 6514609 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.8534. Min Act: -0.1700
Data Index: 8607069 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2915193 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 8045533 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6971. Min Act: -0.1700
Data Index: 660102 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6971. Min Act: -0.1700
Data Index: 3942691 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6659. Min Act: -0.1700
Data Index: 2006682 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6346. Min Act: -0.1700
Data Index: 7975363 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6346. Min Act: -0.1700
Data Index: 1220408 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6346. Min Act: -0.1700
Data Index: 4903391 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6034. Min Act: -0.1700
Data Index: 2998696 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6034. Min Act: -0.1700
Data Index: 8651972 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.5721. Min Act: -0.1700
Data Index: 1164447 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.5409. Min Act: -0.1700
Data Index: 4493042 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.6034. Min Act: -0.1700
Data Index: 3487257 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.5409. Min Act: -0.1700
Data Index: 8322386 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9471. Min Range: -5.9471
Max Act: 5.5409. Min Act: -0.1700
Data Index: 3278506 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19