Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.9808. Min Act: -0.1700
Data Index: 5265737 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.8558. Min Act: -0.1700
Data Index: 1021721 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.7308. Min Act: -0.1700
Data Index: 7566175 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.7621. Min Act: -0.1700
Data Index: 5879084 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.6683. Min Act: -0.1700
Data Index: 3655288 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.6371. Min Act: -0.1700
Data Index: 4481072 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.6058. Min Act: -0.1700
Data Index: 7796265 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.6058. Min Act: -0.1700
Data Index: 7002297 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.6058. Min Act: -0.1700
Data Index: 4078724 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5746. Min Act: -0.1700
Data Index: 6693063 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5433. Min Act: -0.1700
Data Index: 4700652 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5433. Min Act: -0.1700
Data Index: 8527565 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5433. Min Act: -0.1700
Data Index: 4057714 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5433. Min Act: -0.1700
Data Index: 2496495 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5433. Min Act: -0.1700
Data Index: 2007113 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5121. Min Act: -0.1700
Data Index: 576104 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5121. Min Act: -0.1700
Data Index: 6923062 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5121. Min Act: -0.1700
Data Index: 5648382 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5121. Min Act: -0.1700
Data Index: 8192714 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9808. Min Range: -4.9808
Max Act: 4.5121. Min Act: -0.1700
Data Index: 199746 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19