Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.9456. Min Act: -0.1700
Data Index: 7296251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.9143. Min Act: -0.1700
Data Index: 7264992 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 1094205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 6672391 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 6472006 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 4828896 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 818151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 6819993 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 8403678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 487627 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 3514187 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 7854596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 7816842 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8830. Min Act: -0.1700
Data Index: 44844 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 363297 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 6814955 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 2078453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 5154889 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 3600392 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9456. Min Range: -3.9456
Max Act: 3.8518. Min Act: -0.1700
Data Index: 805568 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19