Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6132. Min Range: -7.6132
Max Act: 7.6132. Min Act: -0.1700
Data Index: 7602889 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6132. Min Range: -7.6132
Max Act: 7.0820. Min Act: -0.1700
Data Index: 2897994 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8945. Min Act: -0.1700
Data Index: 2370310 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8945. Min Act: -0.1700
Data Index: 1772135 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8945. Min Act: -0.1700
Data Index: 4098921 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8632. Min Act: -0.1700
Data Index: 1592894 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8632. Min Act: -0.1700
Data Index: 7347942 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.8320. Min Act: -0.1700
Data Index: 5617292 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7695. Min Act: -0.1700
Data Index: 7947953 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5376608 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7382. Min Act: -0.1700
Data Index: 605865 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7382. Min Act: -0.1700
Data Index: 2292031 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7070. Min Act: -0.1700
Data Index: 6208235 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7070. Min Act: -0.1700
Data Index: 255942 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7070. Min Act: -0.1700
Data Index: 1071009 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.7070. Min Act: -0.1700
Data Index: 647465 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.6757. Min Act: -0.1700
Data Index: 6971972 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.6757. Min Act: -0.1700
Data Index: 2171864 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.6757. Min Act: -0.1700
Data Index: 1203487 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6132. Min Range: -7.6132
Max Act: 6.6757. Min Act: -0.1700
Data Index: 8092365 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19