Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4159 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.5668. Min Act: -0.1700
Data Index: 7219716 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.5355. Min Act: -0.1700
Data Index: 7580811 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.5042. Min Act: -0.1700
Data Index: 7219709 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4729. Min Act: -0.1700
Data Index: 3894160 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4572. Min Act: -0.1700
Data Index: 3341882 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4729. Min Act: -0.1700
Data Index: 7219713 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4572. Min Act: -0.1700
Data Index: 5659026 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4415. Min Act: -0.1700
Data Index: 7274612 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4102. Min Act: -0.1700
Data Index: 8305351 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4102. Min Act: -0.1700
Data Index: 1939431 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3788. Min Act: -0.1700
Data Index: 4334372 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3788. Min Act: -0.1700
Data Index: 4133344 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3945. Min Act: -0.1700
Data Index: 1495579 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.4102. Min Act: -0.1700
Data Index: 1381162 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3945. Min Act: -0.1700
Data Index: 383582 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3788. Min Act: -0.1700
Data Index: 1243005 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3632. Min Act: -0.1700
Data Index: 7119786 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3788. Min Act: -0.1700
Data Index: 2132585 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3788. Min Act: -0.1700
Data Index: 2859837 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5668. Min Range: -3.5668
Max Act: 3.3632. Min Act: -0.1700
Data Index: 8103892 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19