Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.8156. Min Act: -0.1700
Data Index: 26023 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.6906. Min Act: -0.1700
Data Index: 7734804 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 7741524 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 6904205 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.5656. Min Act: -0.1700
Data Index: 6591807 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.5344. Min Act: -0.1700
Data Index: 4418723 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.4719. Min Act: -0.1700
Data Index: 4973387 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.4094. Min Act: -0.1700
Data Index: 1741931 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.4094. Min Act: -0.1700
Data Index: 7775086 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.3469. Min Act: -0.1700
Data Index: 4439988 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.3469. Min Act: -0.1700
Data Index: 1806761 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.3469. Min Act: -0.1700
Data Index: 5015919 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.2844. Min Act: -0.1700
Data Index: 4322213 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.2531. Min Act: -0.1700
Data Index: 6720167 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.2219. Min Act: -0.1700
Data Index: 2548424 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.2219. Min Act: -0.1700
Data Index: 7313374 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.2531. Min Act: -0.1700
Data Index: 3444639 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.1906. Min Act: -0.1700
Data Index: 288686 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.1906. Min Act: -0.1700
Data Index: 6195501 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8156. Min Range: -7.8156
Max Act: 7.1594. Min Act: -0.1700
Data Index: 8687715 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19