Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0778. Min Range: -9.0778
Max Act: 9.0778. Min Act: -0.1700
Data Index: 5572985 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0778. Min Range: -9.0778
Max Act: 9.0153. Min Act: -0.1700
Data Index: 1382119 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0778. Min Range: -9.0778
Max Act: 9.0153. Min Act: -0.1700
Data Index: 7235654 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.9528. Min Act: -0.1700
Data Index: 1604252 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 90536 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8903. Min Act: -0.1700
Data Index: 3513167 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8903. Min Act: -0.1700
Data Index: 4009532 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8903. Min Act: -0.1700
Data Index: 7219489 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 4973360 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 4651936 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 502277 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 5852431 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.7653. Min Act: -0.1700
Data Index: 6290283 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 5660962 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 6316385 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 7168736 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 6578720 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.8278. Min Act: -0.1700
Data Index: 6446378 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.7028. Min Act: -0.1700
Data Index: 2543288 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0778. Min Range: -9.0778
Max Act: 8.7653. Min Act: -0.1700
Data Index: 2664691 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19