Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.3031. Min Act: -0.1700
Data Index: 7970897 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1468. Min Act: -0.1700
Data Index: 8457232 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1468. Min Act: -0.1700
Data Index: 6065678 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1156. Min Act: -0.1700
Data Index: 2552926 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1156. Min Act: -0.1700
Data Index: 7621678 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1156. Min Act: -0.1700
Data Index: 3588822 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1156. Min Act: -0.1700
Data Index: 8700309 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 347652 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 550480 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 3269705 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 401092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 5469268 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 1452748 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 8371894 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0843. Min Act: -0.1700
Data Index: 7252535 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 3815565 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 6502376 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 4657157 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 6803787 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2222343 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19