Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1034 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.4041. Min Act: -0.1700
Data Index: 7239537 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.3104. Min Act: -0.1700
Data Index: 2418285 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.0916. Min Act: -0.1700
Data Index: 7780511 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.0916. Min Act: -0.1700
Data Index: 2030790 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.0604. Min Act: -0.1700
Data Index: 6536049 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4041. Min Range: -6.4041
Max Act: 6.0604. Min Act: -0.1700
Data Index: 2217323 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.9979. Min Act: -0.1700
Data Index: 6019105 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.9979. Min Act: -0.1700
Data Index: 4728596 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.9354. Min Act: -0.1700
Data Index: 3540992 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7181106 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7106257 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.8729. Min Act: -0.1700
Data Index: 6950603 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.8416. Min Act: -0.1700
Data Index: 8187 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.8416. Min Act: -0.1700
Data Index: 3644414 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.8416. Min Act: -0.1700
Data Index: 7501760 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.8104. Min Act: -0.1700
Data Index: 7072344 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7174857 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.7791. Min Act: -0.1700
Data Index: 3860632 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4093263 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4041. Min Range: -6.4041
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7295081 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19