Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4391 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3722. Min Act: -0.1700
Data Index: 4160442 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3722. Min Act: -0.1700
Data Index: 7315996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3722. Min Act: -0.1700
Data Index: 7778352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3722. Min Act: -0.1700
Data Index: 1461241 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 5219002 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 5417348 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 6861880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 7683721 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 7744518 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 8218407 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 914818 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 2784110 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3409. Min Act: -0.1700
Data Index: 121386 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 3848384 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 3961246 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 138818 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 3892176 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 3802178 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 304045 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3722. Min Range: -3.3722
Max Act: 3.3095. Min Act: -0.1700
Data Index: 2561501 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19