Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1190. Min Range: -12.1190
Max Act: 12.1190. Min Act: -0.1700
Data Index: 4618017 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.8690. Min Act: -0.1700
Data Index: 5286590 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.8065. Min Act: -0.1700
Data Index: 4166836 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.7440. Min Act: -0.1700
Data Index: 6264736 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.8065. Min Act: -0.1700
Data Index: 5750272 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.6815. Min Act: -0.1700
Data Index: 6699787 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.6815. Min Act: -0.1700
Data Index: 4562633 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.6815. Min Act: -0.1700
Data Index: 2689118 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.6815. Min Act: -0.1700
Data Index: 4618016 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.5565. Min Act: -0.1700
Data Index: 5922673 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.5565. Min Act: -0.1700
Data Index: 7127725 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.6190. Min Act: -0.1700
Data Index: 7004077 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.4940. Min Act: -0.1700
Data Index: 8286331 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.4940. Min Act: -0.1700
Data Index: 2775624 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.4315. Min Act: -0.1700
Data Index: 4113822 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.4315. Min Act: -0.1700
Data Index: 6129472 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.4315. Min Act: -0.1700
Data Index: 2964384 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.3690. Min Act: -0.1700
Data Index: 5304540 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.3065. Min Act: -0.1700
Data Index: 5749205 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1190. Min Range: -12.1190
Max Act: 11.3690. Min Act: -0.1700
Data Index: 4137418 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19