Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.8777. Min Act: -0.1700
Data Index: 307347 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.8777. Min Act: -0.1700
Data Index: 6684596 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6590. Min Act: -0.1700
Data Index: 2604054 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6590. Min Act: -0.1700
Data Index: 5449815 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6590. Min Act: -0.1700
Data Index: 4777973 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6277. Min Act: -0.1700
Data Index: 8317788 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6277. Min Act: -0.1700
Data Index: 3303587 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6277. Min Act: -0.1700
Data Index: 4686996 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.6277. Min Act: -0.1700
Data Index: 318066 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5965. Min Act: -0.1700
Data Index: 8521145 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5965. Min Act: -0.1700
Data Index: 5103140 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5965. Min Act: -0.1700
Data Index: 4269149 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5965. Min Act: -0.1700
Data Index: 1481509 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 6066587 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5965. Min Act: -0.1700
Data Index: 1607052 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 7362718 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 2306329 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 3059375 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 1147491 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8777. Min Range: -4.8777
Max Act: 4.5652. Min Act: -0.1700
Data Index: 5786470 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19