Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5273 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.8739. Min Act: -0.1700
Data Index: 6340458 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.8114. Min Act: -0.1700
Data Index: 880586 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.6864. Min Act: -0.1700
Data Index: 7401867 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.6864. Min Act: -0.1700
Data Index: 125601 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.6239. Min Act: -0.1700
Data Index: 10565 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.6239. Min Act: -0.1700
Data Index: 4371925 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 8165533 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5614. Min Act: -0.1700
Data Index: 5782976 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 4500165 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 5111257 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 4821699 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 2804243 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 8781775 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.6239. Min Act: -0.1700
Data Index: 7932310 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5614. Min Act: -0.1700
Data Index: 7192795 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5302. Min Act: -0.1700
Data Index: 7322953 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5302. Min Act: -0.1700
Data Index: 4508964 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5302. Min Act: -0.1700
Data Index: 2343076 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.4989. Min Act: -0.1700
Data Index: 4674996 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.4989. Min Act: -0.1700
Data Index: 5330649 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19