Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.5906. Min Act: -0.1700
Data Index: 4377954 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.4344. Min Act: -0.1700
Data Index: 542147 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.2469. Min Act: -0.1700
Data Index: 4925744 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.2469. Min Act: -0.1700
Data Index: 6288815 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1844. Min Act: -0.1700
Data Index: 2794213 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1844. Min Act: -0.1700
Data Index: 3410879 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1844. Min Act: -0.1700
Data Index: 2964052 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1844. Min Act: -0.1700
Data Index: 4425176 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4106832 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1219. Min Act: -0.1700
Data Index: 8508271 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.1219. Min Act: -0.1700
Data Index: 8078151 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0906. Min Act: -0.1700
Data Index: 7943489 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0594. Min Act: -0.1700
Data Index: 7937755 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0594. Min Act: -0.1700
Data Index: 5728834 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0594. Min Act: -0.1700
Data Index: 5666514 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0594. Min Act: -0.1700
Data Index: 1102705 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0594. Min Act: -0.1700
Data Index: 6982168 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5906. Min Range: -6.5906
Max Act: 6.0281. Min Act: -0.1700
Data Index: 6562726 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5906. Min Range: -6.5906
Max Act: 5.9969. Min Act: -0.1700
Data Index: 1008549 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5906. Min Range: -6.5906
Max Act: 5.9969. Min Act: -0.1700
Data Index: 5395286 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19