Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.4070. Min Act: -0.1700
Data Index: 5624968 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.3133. Min Act: -0.1700
Data Index: 326966 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.2508. Min Act: -0.1700
Data Index: 3554823 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.2508. Min Act: -0.1650
Data Index: 1932863 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.2195. Min Act: -0.1700
Data Index: 1446791 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.1570. Min Act: -0.1700
Data Index: 5960651 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.1258. Min Act: -0.1700
Data Index: 6150121 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0945. Min Act: -0.1695
Data Index: 7259952 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0945. Min Act: -0.1700
Data Index: 7117375 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0945. Min Act: -0.1700
Data Index: 2880990 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0945. Min Act: -0.1700
Data Index: 3967946 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0633. Min Act: -0.1700
Data Index: 6839567 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0633. Min Act: -0.1700
Data Index: 3666816 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4387038 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0008. Min Act: -0.1700
Data Index: 7651166 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4070. Min Range: -5.4070
Max Act: 4.9695. Min Act: -0.1700
Data Index: 2192203 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4070. Min Range: -5.4070
Max Act: 5.0008. Min Act: -0.1700
Data Index: 8418033 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4070. Min Range: -5.4070
Max Act: 4.9070. Min Act: -0.1674
Data Index: 264628 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4070. Min Range: -5.4070
Max Act: 4.9383. Min Act: -0.1700
Data Index: 2349705 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4070. Min Range: -5.4070
Max Act: 4.9383. Min Act: -0.1700
Data Index: 2241264 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19