Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 951 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0460. Min Range: -6.0460
Max Act: 6.0460. Min Act: -0.1700
Data Index: 3195829 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.6397. Min Act: -0.1700
Data Index: 2149160 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.5460. Min Act: -0.1700
Data Index: 5024223 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.5147. Min Act: -0.1700
Data Index: 8666560 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.4835. Min Act: -0.1700
Data Index: 2876795 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.4522. Min Act: -0.1700
Data Index: 8552856 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.5147. Min Act: -0.1700
Data Index: 2625118 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.4522. Min Act: -0.1700
Data Index: 6749150 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.4210. Min Act: -0.1700
Data Index: 561519 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.4210. Min Act: -0.1700
Data Index: 4401444 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 6708445 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 4944742 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 6049718 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 255011 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 2030351 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 1821914 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 8199966 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 7063980 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 3186021 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0460. Min Range: -6.0460
Max Act: 5.2960. Min Act: -0.1700
Data Index: 3101624 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19