Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0256. Min Range: -6.0256
Max Act: 6.0256. Min Act: -0.1700
Data Index: 5866943 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.9944. Min Act: -0.1700
Data Index: 4879760 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.9631. Min Act: -0.1700
Data Index: 5721016 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1081070 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3184825 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.8694. Min Act: -0.1700
Data Index: 8393021 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.8694. Min Act: -0.1700
Data Index: 693143 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7756. Min Act: -0.1700
Data Index: 5721014 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7756. Min Act: -0.1700
Data Index: 2575976 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7444. Min Act: -0.1700
Data Index: 6212530 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7131. Min Act: -0.1700
Data Index: 2394684 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7131. Min Act: -0.1700
Data Index: 6705710 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3493409 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 4476181 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 18875 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 1683580 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 7131791 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6506. Min Act: -0.1700
Data Index: 3154187 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 8086655 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0256. Min Range: -6.0256
Max Act: 5.6819. Min Act: -0.1700
Data Index: 309757 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19