Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5779 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5357. Min Range: -8.5357
Max Act: 8.5357. Min Act: -0.1700
Data Index: 6186986 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.9107. Min Act: -0.1700
Data Index: 8199389 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.9107. Min Act: -0.1700
Data Index: 884078 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.8482. Min Act: -0.1700
Data Index: 2949 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.8482. Min Act: -0.1700
Data Index: 7103514 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.7232. Min Act: -0.1700
Data Index: 6905973 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.6920. Min Act: -0.1700
Data Index: 6650775 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.6607. Min Act: -0.1700
Data Index: 6272411 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.6920. Min Act: -0.1700
Data Index: 1790626 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.6295. Min Act: -0.1700
Data Index: 8630165 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.6295. Min Act: -0.1700
Data Index: 5843129 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.5982. Min Act: -0.1700
Data Index: 1276625 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.5670. Min Act: -0.1700
Data Index: 5661750 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.5670. Min Act: -0.1700
Data Index: 3796082 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 1861200 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 6771981 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.4107. Min Act: -0.1700
Data Index: 37670 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.4107. Min Act: -0.1700
Data Index: 1305545 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.3795. Min Act: -0.1700
Data Index: 1970912 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5357. Min Range: -8.5357
Max Act: 7.3482. Min Act: -0.1700
Data Index: 2242939 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19