Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.6820. Min Act: -0.1700
Data Index: 871096 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.5570. Min Act: -0.1700
Data Index: 4775242 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.3695. Min Act: -0.1700
Data Index: 6317950 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.2445. Min Act: -0.1700
Data Index: 1859052 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.1195. Min Act: -0.1700
Data Index: 8029843 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6820. Min Range: -10.6820
Max Act: 10.0570. Min Act: -0.1700
Data Index: 5929792 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.9320. Min Act: -0.1700
Data Index: 2867144 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.9320. Min Act: -0.1700
Data Index: 3345515 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.9320. Min Act: -0.1700
Data Index: 4387839 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.9320. Min Act: -0.1700
Data Index: 1355774 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8695. Min Act: -0.1700
Data Index: 711084 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8695. Min Act: -0.1700
Data Index: 7549968 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 5522637 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 117507 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 1003286 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 3292431 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 5674670 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 522775 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 3964916 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6820. Min Range: -10.6820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 1316641 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19