Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.2531. Min Act: -0.1700
Data Index: 4646774 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.2219. Min Act: -0.1700
Data Index: 7360271 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.1906. Min Act: -0.1700
Data Index: 298874 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.1281. Min Act: -0.1700
Data Index: 552237 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.0031. Min Act: -0.1700
Data Index: 6948555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2531. Min Range: -5.2531
Max Act: 5.0031. Min Act: -0.1700
Data Index: 4328920 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.9719. Min Act: -0.1700
Data Index: 2898365 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.9406. Min Act: -0.1700
Data Index: 6313273 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.9094. Min Act: -0.1700
Data Index: 2553725 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8781. Min Act: -0.1700
Data Index: 3403116 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8781. Min Act: -0.1700
Data Index: 6948549 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8156. Min Act: -0.1700
Data Index: 6948552 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8469. Min Act: -0.1700
Data Index: 905105 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8156. Min Act: -0.1700
Data Index: 336169 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.8156. Min Act: -0.1700
Data Index: 298870 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.7844. Min Act: -0.1700
Data Index: 4328921 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.7844. Min Act: -0.1700
Data Index: 5658237 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.7844. Min Act: -0.1700
Data Index: 494880 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.7219. Min Act: -0.1700
Data Index: 2720472 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2531. Min Range: -5.2531
Max Act: 4.7844. Min Act: -0.1700
Data Index: 3407648 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19