Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.3318. Min Act: -0.1700
Data Index: 1937907 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.2495. Min Act: -0.1700
Data Index: 2372238 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.2330. Min Act: -0.1700
Data Index: 1680480 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.2330. Min Act: -0.1700
Data Index: 7676449 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.2164. Min Act: -0.1697
Data Index: 3379957 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1998. Min Act: -0.1700
Data Index: 3189140 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1998. Min Act: -0.1700
Data Index: 3962078 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1998. Min Act: -0.1699
Data Index: 8466647 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1998. Min Act: -0.1700
Data Index: 1552364 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 3324529 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 4627018 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 5629658 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1998. Min Act: -0.1685
Data Index: 3597407 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 2967536 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 5711094 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 6050646 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 8607090 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1832. Min Act: -0.1700
Data Index: 112475 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1666. Min Act: -0.1700
Data Index: 2717929 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3318. Min Range: -2.3318
Max Act: 2.1666. Min Act: -0.1700
Data Index: 3555915 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19