Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2281 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3290. Min Range: -7.3290
Max Act: 7.3290. Min Act: -0.1700
Data Index: 4569982 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3290. Min Range: -7.3290
Max Act: 7.2040. Min Act: -0.1700
Data Index: 6777563 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3290. Min Range: -7.3290
Max Act: 7.1728. Min Act: -0.1700
Data Index: 8029344 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3290. Min Range: -7.3290
Max Act: 7.0165. Min Act: -0.1700
Data Index: 7059578 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.9540. Min Act: -0.1700
Data Index: 5097512 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.9228. Min Act: -0.1700
Data Index: 6828412 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.9228. Min Act: -0.1700
Data Index: 2567847 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.8603. Min Act: -0.1700
Data Index: 223305 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.8603. Min Act: -0.1700
Data Index: 8029345 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.8290. Min Act: -0.1700
Data Index: 3276241 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7978. Min Act: -0.1700
Data Index: 6670882 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7978. Min Act: -0.1700
Data Index: 416943 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7353. Min Act: -0.1700
Data Index: 223306 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7665. Min Act: -0.1700
Data Index: 6975097 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7353. Min Act: -0.1700
Data Index: 6386772 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7353. Min Act: -0.1700
Data Index: 6386791 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7353. Min Act: -0.1700
Data Index: 2567848 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7353. Min Act: -0.1700
Data Index: 5302511 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7040. Min Act: -0.1700
Data Index: 4390691 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3290. Min Range: -7.3290
Max Act: 6.7040. Min Act: -0.1700
Data Index: 2900551 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19