Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.2752. Min Act: -0.1700
Data Index: 1445937 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.2752. Min Act: -0.1700
Data Index: 2553686 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.1815. Min Act: -0.1700
Data Index: 7485456 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.1190. Min Act: -0.1700
Data Index: 4616863 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 538643 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9940. Min Act: -0.1700
Data Index: 8291448 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2752. Min Range: -6.2752
Max Act: 6.0252. Min Act: -0.1700
Data Index: 1442832 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9940. Min Act: -0.1700
Data Index: 8459872 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9940. Min Act: -0.1700
Data Index: 5511133 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9315. Min Act: -0.1700
Data Index: 3644467 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4745136 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9315. Min Act: -0.1700
Data Index: 1459344 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8690. Min Act: -0.1700
Data Index: 4098293 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.9002. Min Act: -0.1700
Data Index: 4397505 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8690. Min Act: -0.1700
Data Index: 6081030 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8377. Min Act: -0.1700
Data Index: 6718192 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8377. Min Act: -0.1700
Data Index: 8273545 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8377. Min Act: -0.1700
Data Index: 5449198 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.7752. Min Act: -0.1700
Data Index: 24269 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2752. Min Range: -6.2752
Max Act: 5.8065. Min Act: -0.1700
Data Index: 465867 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19