Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1105 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.9715. Min Act: -0.1700
Data Index: 7950967 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.9090. Min Act: -0.1700
Data Index: 213207 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.8465. Min Act: -0.1700
Data Index: 8681247 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.8152. Min Act: -0.1700
Data Index: 4832502 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8285755 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6902. Min Act: -0.1700
Data Index: 6849140 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6902. Min Act: -0.1700
Data Index: 321365 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6902. Min Act: -0.1700
Data Index: 5771165 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.7215. Min Act: -0.1700
Data Index: 196990 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4086511 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6590. Min Act: -0.1700
Data Index: 6430729 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6277. Min Act: -0.1700
Data Index: 1968316 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6277. Min Act: -0.1700
Data Index: 5216531 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6277. Min Act: -0.1700
Data Index: 4759514 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6277. Min Act: -0.1700
Data Index: 2903634 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.5965. Min Act: -0.1700
Data Index: 7719214 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.5965. Min Act: -0.1700
Data Index: 7555676 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.6277. Min Act: -0.1700
Data Index: 8551060 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.5965. Min Act: -0.1700
Data Index: 447656 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9715. Min Range: -5.9715
Max Act: 5.5965. Min Act: -0.1700
Data Index: 7077666 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19