Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.5992. Min Act: -0.1700
Data Index: 1550795 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.4117. Min Act: -0.1700
Data Index: 3150232 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.3492. Min Act: -0.1700
Data Index: 4451691 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.2242. Min Act: -0.1700
Data Index: 1167182 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.2242. Min Act: -0.1700
Data Index: 7435616 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.1617. Min Act: -0.1700
Data Index: 3600516 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5992. Min Range: -8.5992
Max Act: 8.0367. Min Act: -0.1700
Data Index: 1403290 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.9429. Min Act: -0.1700
Data Index: 2965015 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.9117. Min Act: -0.1700
Data Index: 3824565 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.9117. Min Act: -0.1700
Data Index: 4913795 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.8492. Min Act: -0.1700
Data Index: 353633 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.8179. Min Act: -0.1700
Data Index: 3778674 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7867. Min Act: -0.1700
Data Index: 8262110 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.8179. Min Act: -0.1700
Data Index: 4974393 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7867. Min Act: -0.1700
Data Index: 2441935 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7867. Min Act: -0.1700
Data Index: 6112771 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7867. Min Act: -0.1700
Data Index: 669706 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7242. Min Act: -0.1700
Data Index: 2626932 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7867. Min Act: -0.1700
Data Index: 6317420 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5992. Min Range: -8.5992
Max Act: 7.7242. Min Act: -0.1700
Data Index: 5470085 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19