Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.4762. Min Act: -0.1700
Data Index: 608381 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3512. Min Act: -0.1700
Data Index: 6861431 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3825. Min Act: -0.1700
Data Index: 1180975 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3825. Min Act: -0.1700
Data Index: 6809176 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3825. Min Act: -0.1700
Data Index: 5292046 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3825. Min Act: -0.1700
Data Index: 2172142 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3200. Min Act: -0.1700
Data Index: 7641302 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3200. Min Act: -0.1700
Data Index: 3114782 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3200. Min Act: -0.1700
Data Index: 3665433 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3200. Min Act: -0.1700
Data Index: 6341683 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.3200. Min Act: -0.1700
Data Index: 5740603 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 1656153 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 1246882 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2575. Min Act: -0.1700
Data Index: 7914995 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2575. Min Act: -0.1700
Data Index: 2295234 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 5976218 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2575. Min Act: -0.1700
Data Index: 3762557 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.2262. Min Act: -0.1700
Data Index: 4379663 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.1950. Min Act: -0.1700
Data Index: 1678191 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4762. Min Range: -6.4762
Max Act: 6.1950. Min Act: -0.1700
Data Index: 5228029 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19