Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2536. Min Range: -7.2536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 4726788 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.8473. Min Act: -0.1700
Data Index: 2216866 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6911. Min Act: -0.1700
Data Index: 2340806 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6911. Min Act: -0.1700
Data Index: 2576329 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6911. Min Act: -0.1700
Data Index: 830548 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 1509239 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 7825557 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 2447326 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 6344381 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5973. Min Act: -0.1700
Data Index: 443845 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5973. Min Act: -0.1700
Data Index: 8708234 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5661. Min Act: -0.1700
Data Index: 6986776 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5661. Min Act: -0.1700
Data Index: 2576327 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5348. Min Act: -0.1700
Data Index: 2451599 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5036. Min Act: -0.1700
Data Index: 830547 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5036. Min Act: -0.1700
Data Index: 6304530 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5036. Min Act: -0.1700
Data Index: 830549 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5036. Min Act: -0.1700
Data Index: 443843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.4723. Min Act: -0.1700
Data Index: 3793392 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.4723. Min Act: -0.1700
Data Index: 2218702 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19