Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.6913. Min Act: -0.1700
Data Index: 5176554 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.6913. Min Act: -0.1700
Data Index: 3458272 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4333114 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.6288. Min Act: -0.1700
Data Index: 2848285 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.5976. Min Act: -0.1700
Data Index: 6016895 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.5351. Min Act: -0.1700
Data Index: 4222121 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4726. Min Act: -0.1700
Data Index: 213335 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4726. Min Act: -0.1700
Data Index: 2242055 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 5538322 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 5076 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4413. Min Act: -0.1700
Data Index: 6449585 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 48654 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 1219128 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 7859860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.4101. Min Act: -0.1700
Data Index: 7305517 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.3788. Min Act: -0.1700
Data Index: 8766413 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.3476. Min Act: -0.1700
Data Index: 8304704 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.3476. Min Act: -0.1700
Data Index: 3850731 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.3476. Min Act: -0.1700
Data Index: 5648894 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6913. Min Range: -4.6913
Max Act: 4.3476. Min Act: -0.1700
Data Index: 7499143 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19