Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2219. Min Range: -3.2219
Max Act: 3.2219. Min Act: -0.1700
Data Index: 1925635 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2219. Min Range: -3.2219
Max Act: 3.1433. Min Act: -0.1700
Data Index: 88479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2219. Min Range: -3.2219
Max Act: 3.0645. Min Act: -0.1700
Data Index: 4114999 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2219. Min Range: -3.2219
Max Act: 3.0329. Min Act: -0.1700
Data Index: 100150 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.9855. Min Act: -0.1700
Data Index: 1556880 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.9222. Min Act: -0.1700
Data Index: 3753451 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.9222. Min Act: -0.1700
Data Index: 2067 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.8905. Min Act: -0.1700
Data Index: 6988671 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.8746. Min Act: -0.1700
Data Index: 1643663 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.8428. Min Act: -0.1700
Data Index: 4429163 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7792. Min Act: -0.1700
Data Index: 3791641 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7632. Min Act: -0.1700
Data Index: 7501200 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7473. Min Act: -0.1700
Data Index: 5461255 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7313. Min Act: -0.1700
Data Index: 3443621 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7153. Min Act: -0.1700
Data Index: 7519693 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.6833. Min Act: -0.1700
Data Index: 6521200 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7313. Min Act: -0.1700
Data Index: 3031100 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7313. Min Act: -0.1700
Data Index: 5101135 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.7153. Min Act: -0.1700
Data Index: 7364428 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2219. Min Range: -3.2219
Max Act: 2.6993. Min Act: -0.1700
Data Index: 3496305 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19