Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5137 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3428. Min Range: -7.3428
Max Act: 7.3428. Min Act: -0.1700
Data Index: 4597722 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3428. Min Range: -7.3428
Max Act: 7.2803. Min Act: -0.1700
Data Index: 1154197 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3428. Min Range: -7.3428
Max Act: 7.0616. Min Act: -0.1700
Data Index: 6450503 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3428. Min Range: -7.3428
Max Act: 7.0616. Min Act: -0.1700
Data Index: 6753063 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3428. Min Range: -7.3428
Max Act: 7.0303. Min Act: -0.1700
Data Index: 2685151 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.9366. Min Act: -0.1700
Data Index: 6572347 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.9366. Min Act: -0.1700
Data Index: 7428078 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.9053. Min Act: -0.1700
Data Index: 6474569 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.9053. Min Act: -0.1700
Data Index: 6094948 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.9053. Min Act: -0.1700
Data Index: 7134652 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8741. Min Act: -0.1700
Data Index: 168805 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8741. Min Act: -0.1700
Data Index: 8448576 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8116. Min Act: -0.1700
Data Index: 2037954 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8428. Min Act: -0.1700
Data Index: 2192178 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8428. Min Act: -0.1700
Data Index: 7356453 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8428. Min Act: -0.1700
Data Index: 1350156 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8428. Min Act: -0.1700
Data Index: 5380425 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.8116. Min Act: -0.1700
Data Index: 2688751 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.7803. Min Act: -0.1700
Data Index: 7874498 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3428. Min Range: -7.3428
Max Act: 6.7803. Min Act: -0.1700
Data Index: 8295640 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19