Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5957 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.4633. Min Act: -0.1700
Data Index: 648130 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.4633. Min Act: -0.1700
Data Index: 5066950 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.4008. Min Act: -0.1700
Data Index: 1259503 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.4008. Min Act: -0.1700
Data Index: 4000625 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.3695. Min Act: -0.1700
Data Index: 2923017 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.2445. Min Act: -0.1700
Data Index: 4057116 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.2758. Min Act: -0.1700
Data Index: 6199282 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.2133. Min Act: -0.1700
Data Index: 8797360 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1508. Min Act: -0.1700
Data Index: 1835354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1508. Min Act: -0.1700
Data Index: 5474471 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1508. Min Act: -0.1700
Data Index: 8473088 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6644927 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3691771 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1195. Min Act: -0.1700
Data Index: 4357777 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.0883. Min Act: -0.1700
Data Index: 623357 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.1195. Min Act: -0.1700
Data Index: 2905014 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.0570. Min Act: -0.1700
Data Index: 4825933 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.0570. Min Act: -0.1700
Data Index: 3119718 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.0258. Min Act: -0.1700
Data Index: 2748757 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4633. Min Range: -6.4633
Max Act: 6.0258. Min Act: -0.1700
Data Index: 3168066 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19