Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.1898. Min Act: -0.1700
Data Index: 3493654 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.1586. Min Act: -0.1700
Data Index: 500068 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.0335. Min Act: -0.1700
Data Index: 5130486 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.0023. Min Act: -0.1700
Data Index: 7317512 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.0023. Min Act: -0.1700
Data Index: 7837793 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1898. Min Range: -4.1898
Max Act: 4.0023. Min Act: -0.1700
Data Index: 6200301 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 2435037 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 6995772 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 8585874 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 2454056 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 5977567 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9085. Min Act: -0.1700
Data Index: 1003828 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 1298197 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 3425220 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 6294256 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9710. Min Act: -0.1700
Data Index: 7112630 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 4575255 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 5005680 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 2236677 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1898. Min Range: -4.1898
Max Act: 3.9398. Min Act: -0.1700
Data Index: 7450488 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19