Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.5350. Min Act: -0.1700
Data Index: 1831364 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.5350. Min Act: -0.1700
Data Index: 7526409 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.4413. Min Act: -0.1700
Data Index: 7443177 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.4725. Min Act: -0.1700
Data Index: 4706894 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3788. Min Act: -0.1700
Data Index: 4250023 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.4413. Min Act: -0.1700
Data Index: 5490784 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.4100. Min Act: -0.1700
Data Index: 6105708 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3788. Min Act: -0.1700
Data Index: 2558000 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.4100. Min Act: -0.1700
Data Index: 2675727 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3163. Min Act: -0.1700
Data Index: 6195062 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 2400504 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 2378684 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 1737883 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 24464 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3163. Min Act: -0.1700
Data Index: 3357685 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 2158586 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3163. Min Act: -0.1700
Data Index: 1855963 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3929590 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3929589 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5350. Min Range: -5.5350
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1186281 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19