Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4483 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.5564. Min Act: -0.1700
Data Index: 1930957 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.3689. Min Act: -0.1700
Data Index: 5368617 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.2752. Min Act: -0.1700
Data Index: 1154189 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.2752. Min Act: -0.1700
Data Index: 4232503 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.2127. Min Act: -0.1700
Data Index: 3260591 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.0564. Min Act: -0.1700
Data Index: 186190 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5564. Min Range: -6.5564
Max Act: 6.0564. Min Act: -0.1700
Data Index: 6453496 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9939. Min Act: -0.1700
Data Index: 2627471 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9939. Min Act: -0.1700
Data Index: 3618121 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9939. Min Act: -0.1700
Data Index: 3205074 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4879233 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9314. Min Act: -0.1700
Data Index: 1605788 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9314. Min Act: -0.1700
Data Index: 8164720 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9314. Min Act: -0.1700
Data Index: 5295234 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.9314. Min Act: -0.1700
Data Index: 4204392 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3610923 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.8377. Min Act: -0.1700
Data Index: 816008 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3590954 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.8064. Min Act: -0.1700
Data Index: 239246 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5564. Min Range: -6.5564
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2855915 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19