Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 380 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 6810163 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7160812 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0292. Min Act: -0.1700
Data Index: 2646327 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0292. Min Act: -0.1700
Data Index: 4057882 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7335118 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1700
Data Index: 6571567 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1700
Data Index: 4578637 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1698
Data Index: 8750360 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1700
Data Index: 2779091 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1700
Data Index: 1014726 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 8799197 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 5082997 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7844777 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 8459195 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 7377213 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 5462647 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1697
Data Index: 5446389 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 584182 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 2333216 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 3872019 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19