Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.5332. Min Act: -0.1700
Data Index: 3914814 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.5069. Min Act: -0.1700
Data Index: 299735 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4893. Min Act: -0.1689
Data Index: 2000411 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.5069. Min Act: -0.1700
Data Index: 7954067 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4893. Min Act: -0.1700
Data Index: 7636204 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4893. Min Act: -0.1700
Data Index: 525316 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4893. Min Act: -0.1685
Data Index: 6104829 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4805. Min Act: -0.1700
Data Index: 4185148 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4805. Min Act: -0.1700
Data Index: 7152663 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4717. Min Act: -0.1700
Data Index: 6793580 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4717. Min Act: -0.1700
Data Index: 713906 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4630. Min Act: -0.1700
Data Index: 693625 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4630. Min Act: -0.1700
Data Index: 7327951 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4717. Min Act: -0.1700
Data Index: 6975568 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4542. Min Act: -0.1700
Data Index: 4692016 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4454. Min Act: -0.1700
Data Index: 1812184 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4366. Min Act: -0.1700
Data Index: 3332721 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4454. Min Act: -0.1700
Data Index: 6207034 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4542. Min Act: -0.1700
Data Index: 2631449 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5332. Min Range: -1.5332
Max Act: 1.4454. Min Act: -0.1700
Data Index: 750862 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19