Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 144 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.7698. Min Act: -0.1700
Data Index: 2142505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.4966. Min Act: -0.1700
Data Index: 5230737 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.4966. Min Act: -0.1700
Data Index: 2109470 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.4804. Min Act: -0.1700
Data Index: 8671680 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.4642. Min Act: -0.1700
Data Index: 2720737 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.4479. Min Act: -0.1700
Data Index: 4385788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3991. Min Act: -0.1700
Data Index: 5500402 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3991. Min Act: -0.1700
Data Index: 864194 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3827. Min Act: -0.1700
Data Index: 3183454 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3991. Min Act: -0.1700
Data Index: 763571 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3664. Min Act: -0.1700
Data Index: 2132816 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3664. Min Act: -0.1700
Data Index: 3793443 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3664. Min Act: -0.1700
Data Index: 3124884 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3500. Min Act: -0.1700
Data Index: 8328816 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3336. Min Act: -0.1700
Data Index: 5479117 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3500. Min Act: -0.1700
Data Index: 7365210 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3172. Min Act: -0.1700
Data Index: 422991 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3172. Min Act: -0.1700
Data Index: 3066802 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3172. Min Act: -0.1700
Data Index: 2796498 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7698. Min Range: -2.7698
Max Act: 2.3336. Min Act: -0.1700
Data Index: 6510668 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19