Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.9511. Min Act: -0.1700
Data Index: 7133086 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.8886. Min Act: -0.1700
Data Index: 1246089 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.7324. Min Act: -0.1700
Data Index: 1789113 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.6386. Min Act: -0.1700
Data Index: 2887623 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.6386. Min Act: -0.1700
Data Index: 7555285 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5449. Min Act: -0.1700
Data Index: 623529 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5761. Min Act: -0.1700
Data Index: 4849096 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5449. Min Act: -0.1700
Data Index: 4621215 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5136. Min Act: -0.1700
Data Index: 1101993 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5136. Min Act: -0.1700
Data Index: 186253 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5136. Min Act: -0.1700
Data Index: 7647445 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 4311951 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 4634117 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 5396988 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 5491750 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4199. Min Act: -0.1700
Data Index: 1630940 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4199. Min Act: -0.1700
Data Index: 3472653 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4199. Min Act: -0.1700
Data Index: 4032393 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4199. Min Act: -0.1700
Data Index: 8178781 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4199. Min Act: -0.1700
Data Index: 2278011 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19