Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.1790. Min Act: -0.1700
Data Index: 7498128 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.1165. Min Act: -0.1700
Data Index: 2042969 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4365839 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0852. Min Act: -0.1700
Data Index: 7936163 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0852. Min Act: -0.1700
Data Index: 3288279 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4658024 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0539. Min Act: -0.1700
Data Index: 7936162 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0539. Min Act: -0.1700
Data Index: 4846025 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9914. Min Act: -0.1700
Data Index: 4690840 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9914. Min Act: -0.1700
Data Index: 8596089 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1790. Min Range: -4.1790
Max Act: 4.0227. Min Act: -0.1700
Data Index: 4658025 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9914. Min Act: -0.1700
Data Index: 4658026 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9602. Min Act: -0.1700
Data Index: 5382415 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9289. Min Act: -0.1700
Data Index: 2766841 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9289. Min Act: -0.1700
Data Index: 2021017 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9289. Min Act: -0.1700
Data Index: 7936159 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.9289. Min Act: -0.1700
Data Index: 6305620 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.8976. Min Act: -0.1700
Data Index: 4991200 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.8976. Min Act: -0.1700
Data Index: 3016752 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1790. Min Range: -4.1790
Max Act: 3.8976. Min Act: -0.1700
Data Index: 6937554 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19