Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.6305. Min Act: -0.1700
Data Index: 3554608 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.4430. Min Act: -0.1700
Data Index: 599402 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.3805. Min Act: -0.1700
Data Index: 3339919 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.3492. Min Act: -0.1700
Data Index: 5883668 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.3492. Min Act: -0.1700
Data Index: 5096924 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.3180. Min Act: -0.1700
Data Index: 493349 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.3180. Min Act: -0.1700
Data Index: 4010426 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.2555. Min Act: -0.1700
Data Index: 7734068 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.2555. Min Act: -0.1700
Data Index: 5343046 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 6423111 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1930. Min Act: -0.1700
Data Index: 8661966 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1930. Min Act: -0.1700
Data Index: 8749877 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.2242. Min Act: -0.1700
Data Index: 1703767 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 2060915 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 3530914 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 5483615 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 1978166 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1305. Min Act: -0.1700
Data Index: 5221952 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 424525 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6305. Min Range: -5.6305
Max Act: 5.1617. Min Act: -0.1700
Data Index: 4178825 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19