Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.5938. Min Act: -0.1700
Data Index: 2416789 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.2500. Min Act: -0.1700
Data Index: 2093428 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.2500. Min Act: -0.1700
Data Index: 1403919 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.2500. Min Act: -0.1700
Data Index: 997270 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.2188. Min Act: -0.1700
Data Index: 3485102 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.1563. Min Act: -0.1700
Data Index: 3470525 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7865558 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.1563. Min Act: -0.1700
Data Index: 50815 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.1563. Min Act: -0.1700
Data Index: 5923036 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.1563. Min Act: -0.1700
Data Index: 3906419 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 3843843 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 1282551 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 3433935 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0625. Min Act: -0.1700
Data Index: 3970312 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4314021 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0313. Min Act: -0.1700
Data Index: 6702280 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0000. Min Act: -0.1700
Data Index: 8580847 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5938. Min Range: -6.5938
Max Act: 6.0000. Min Act: -0.1700
Data Index: 1891407 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5938. Min Range: -6.5938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 4045509 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5938. Min Range: -6.5938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2038542 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19