Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.3760. Min Act: -0.1700
Data Index: 3822574 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.2510. Min Act: -0.1700
Data Index: 1072531 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.2510. Min Act: -0.1700
Data Index: 1565302 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.2510. Min Act: -0.1700
Data Index: 3619493 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.0635. Min Act: -0.1700
Data Index: 3702090 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.1260. Min Act: -0.1700
Data Index: 1005234 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.0635. Min Act: -0.1700
Data Index: 829955 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.9385. Min Act: -0.1700
Data Index: 1936050 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.0010. Min Act: -0.1700
Data Index: 8761197 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3760. Min Range: -9.3760
Max Act: 9.0010. Min Act: -0.1700
Data Index: 7189130 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.9385. Min Act: -0.1700
Data Index: 4620800 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.9385. Min Act: -0.1700
Data Index: 8267549 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.9385. Min Act: -0.1700
Data Index: 5282116 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8760. Min Act: -0.1700
Data Index: 667062 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.9385. Min Act: -0.1700
Data Index: 1317926 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8760. Min Act: -0.1700
Data Index: 7537299 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8760. Min Act: -0.1700
Data Index: 7360393 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8760. Min Act: -0.1700
Data Index: 1147856 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8760. Min Act: -0.1700
Data Index: 2130622 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3760. Min Range: -9.3760
Max Act: 8.8135. Min Act: -0.1700
Data Index: 749535 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19