Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4936876 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5415. Min Act: -0.1700
Data Index: 8547730 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.3540. Min Act: -0.1700
Data Index: 6525845 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2915. Min Act: -0.1700
Data Index: 4269869 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.1040. Min Act: -0.1700
Data Index: 5308473 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4614367 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.0102. Min Act: -0.1700
Data Index: 3212729 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 8400477 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 8367607 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 3267994 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.8227. Min Act: -0.1700
Data Index: 288478 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.8227. Min Act: -0.1700
Data Index: 4205801 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 5818677 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 7703869 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 5412108 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 8414370 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 2122419 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 842719 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 79874 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5727. Min Range: -5.5727
Max Act: 4.6977. Min Act: -0.1700
Data Index: 6818374 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19