Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1957. Min Range: -7.1957
Max Act: 7.1957. Min Act: -0.1700
Data Index: 1545296 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1957. Min Range: -7.1957
Max Act: 7.1957. Min Act: -0.1700
Data Index: 1969993 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.9769. Min Act: -0.1700
Data Index: 94535 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.9457. Min Act: -0.1700
Data Index: 7935564 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1009170 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.9457. Min Act: -0.1700
Data Index: 1513629 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1142218 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.8519. Min Act: -0.1700
Data Index: 689407 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.8832. Min Act: -0.1700
Data Index: 865578 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.8832. Min Act: -0.1700
Data Index: 4797751 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.8207. Min Act: -0.1700
Data Index: 5209018 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.7582. Min Act: -0.1700
Data Index: 4771493 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.7582. Min Act: -0.1700
Data Index: 7946332 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.7582. Min Act: -0.1700
Data Index: 4952734 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.6957. Min Act: -0.1700
Data Index: 454741 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.7269. Min Act: -0.1700
Data Index: 7759036 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.6957. Min Act: -0.1700
Data Index: 6537245 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.6644. Min Act: -0.1700
Data Index: 7828096 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.6332. Min Act: -0.1700
Data Index: 4675914 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1957. Min Range: -7.1957
Max Act: 6.6332. Min Act: -0.1700
Data Index: 2438104 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19