Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.9374. Min Act: -0.1700
Data Index: 7423697 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.8436. Min Act: -0.1700
Data Index: 6087030 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7811. Min Act: -0.1700
Data Index: 1256407 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7811. Min Act: -0.1700
Data Index: 2928002 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7499. Min Act: -0.1700
Data Index: 21704 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7499. Min Act: -0.1700
Data Index: 5178927 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7811. Min Act: -0.1700
Data Index: 6439281 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7186. Min Act: -0.1700
Data Index: 2426865 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.7186. Min Act: -0.1700
Data Index: 6604372 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.6874. Min Act: -0.1700
Data Index: 2928000 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.6249. Min Act: -0.1700
Data Index: 4999311 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.6249. Min Act: -0.1700
Data Index: 6423221 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5936. Min Act: -0.1700
Data Index: 3914902 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5624. Min Act: -0.1700
Data Index: 5612387 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5936. Min Act: -0.1700
Data Index: 5927019 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.6249. Min Act: -0.1700
Data Index: 6604371 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5936. Min Act: -0.1700
Data Index: 6333265 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5624. Min Act: -0.1700
Data Index: 8087494 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5311. Min Act: -0.1700
Data Index: 4895342 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9374. Min Range: -4.9374
Max Act: 4.5311. Min Act: -0.1700
Data Index: 3545326 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19