Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 559 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.3871. Min Act: -0.1700
Data Index: 5502534 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1511489 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.2934. Min Act: -0.1700
Data Index: 8403163 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.3871. Min Act: -0.1700
Data Index: 1708386 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.2309. Min Act: -0.1700
Data Index: 640541 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.3246. Min Act: -0.1700
Data Index: 986646 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7381050 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.3559. Min Act: -0.1700
Data Index: 7605747 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.2621. Min Act: -0.1700
Data Index: 2575006 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.2309. Min Act: -0.1700
Data Index: 385664 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3234098 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1684. Min Act: -0.1700
Data Index: 1621853 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1684. Min Act: -0.1700
Data Index: 5031435 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.0746. Min Act: -0.1700
Data Index: 8345569 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1371. Min Act: -0.1700
Data Index: 7098077 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1059. Min Act: -0.1700
Data Index: 8029498 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.1059. Min Act: -0.1700
Data Index: 2290504 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.0433. Min Act: -0.1700
Data Index: 6601807 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.0746. Min Act: -0.1700
Data Index: 91084 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3871. Min Range: -4.3871
Max Act: 4.0746. Min Act: -0.1700
Data Index: 7867757 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19