Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1865. Min Range: -7.1865
Max Act: 7.1865. Min Act: -0.1700
Data Index: 1898527 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.9365. Min Act: -0.1700
Data Index: 3057835 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.7803. Min Act: -0.1700
Data Index: 6955996 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.7178. Min Act: -0.1700
Data Index: 8068326 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.6553. Min Act: -0.1700
Data Index: 1663797 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.6553. Min Act: -0.1700
Data Index: 2276903 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.5928. Min Act: -0.1700
Data Index: 2832069 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.5303. Min Act: -0.1700
Data Index: 4753023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.5303. Min Act: -0.1700
Data Index: 5313967 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.5303. Min Act: -0.1700
Data Index: 5871982 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.5303. Min Act: -0.1700
Data Index: 3569256 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.4990. Min Act: -0.1700
Data Index: 4210174 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.4053. Min Act: -0.1700
Data Index: 1582038 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.3740. Min Act: -0.1700
Data Index: 3057836 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.3740. Min Act: -0.1700
Data Index: 4963307 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.3428. Min Act: -0.1700
Data Index: 1418095 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.3428. Min Act: -0.1700
Data Index: 1837370 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.3428. Min Act: -0.1700
Data Index: 6698306 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.2803. Min Act: -0.1700
Data Index: 371094 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1865. Min Range: -7.1865
Max Act: 6.2803. Min Act: -0.1700
Data Index: 3940196 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19