Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1392. Min Range: -4.1392
Max Act: 4.1392. Min Act: -0.1700
Data Index: 1412212 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1392. Min Range: -4.1392
Max Act: 4.1080. Min Act: -0.1700
Data Index: 1514062 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1392. Min Range: -4.1392
Max Act: 4.0455. Min Act: -0.1700
Data Index: 746550 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1392. Min Range: -4.1392
Max Act: 4.0767. Min Act: -0.1700
Data Index: 5747264 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.9829. Min Act: -0.1700
Data Index: 2259647 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.9517. Min Act: -0.1700
Data Index: 6227249 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8891. Min Act: -0.1700
Data Index: 4488980 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8891. Min Act: -0.1700
Data Index: 6015280 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8891. Min Act: -0.1700
Data Index: 5748999 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8579. Min Act: -0.1700
Data Index: 392719 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8891. Min Act: -0.1700
Data Index: 1241912 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8579. Min Act: -0.1700
Data Index: 1488714 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8579. Min Act: -0.1700
Data Index: 6896588 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8266. Min Act: -0.1700
Data Index: 440832 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.7953. Min Act: -0.1700
Data Index: 3507074 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8266. Min Act: -0.1700
Data Index: 5591805 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8266. Min Act: -0.1700
Data Index: 2759395 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.8266. Min Act: -0.1700
Data Index: 4034230 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.7953. Min Act: -0.1700
Data Index: 1305553 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1392. Min Range: -4.1392
Max Act: 3.7953. Min Act: -0.1700
Data Index: 1672685 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19