Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1735 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6881798 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.5531. Min Act: -0.1700
Data Index: 6427363 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.5531. Min Act: -0.1700
Data Index: 1312542 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.4594. Min Act: -0.1700
Data Index: 3291874 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.3969. Min Act: -0.1700
Data Index: 1312541 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8706145 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.2719. Min Act: -0.1700
Data Index: 1113205 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.2406. Min Act: -0.1700
Data Index: 7122036 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7488990 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1781. Min Act: -0.1700
Data Index: 4253277 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1781. Min Act: -0.1700
Data Index: 8792542 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1781. Min Act: -0.1700
Data Index: 5779625 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1469. Min Act: -0.1700
Data Index: 5418477 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 5047675 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 2954265 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 1241378 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 6079233 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.0844. Min Act: -0.1700
Data Index: 7379979 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.0844. Min Act: -0.1700
Data Index: 1152830 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7406. Min Range: -5.7406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 6437426 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19