Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.2024. Min Act: -0.1700
Data Index: 6518246 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.2024. Min Act: -0.1700
Data Index: 6369166 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1712. Min Act: -0.1700
Data Index: 1005205 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1399. Min Act: -0.1700
Data Index: 7949816 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.0774. Min Act: -0.1700
Data Index: 4201050 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.0774. Min Act: -0.1700
Data Index: 3614369 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.0462. Min Act: -0.1700
Data Index: 987232 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9836. Min Act: -0.1700
Data Index: 3959922 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9836. Min Act: -0.1700
Data Index: 1510980 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9524. Min Act: -0.1700
Data Index: 1509968 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9836. Min Act: -0.1700
Data Index: 3333065 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9211. Min Act: -0.1700
Data Index: 216879 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9211. Min Act: -0.1700
Data Index: 8703001 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9211. Min Act: -0.1700
Data Index: 1653435 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9524. Min Act: -0.1700
Data Index: 5075081 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9524. Min Act: -0.1700
Data Index: 4863951 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.9211. Min Act: -0.1700
Data Index: 2260256 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.8898. Min Act: -0.1700
Data Index: 3878564 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.8898. Min Act: -0.1700
Data Index: 6345606 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2024. Min Range: -4.2024
Max Act: 3.8898. Min Act: -0.1700
Data Index: 7171375 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19