Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2787163 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.1092. Min Act: -0.1700
Data Index: 8829467 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0779. Min Act: -0.1700
Data Index: 7888507 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0779. Min Act: -0.1699
Data Index: 6379161 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0154. Min Act: -0.1700
Data Index: 4803638 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1751643 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0779. Min Act: -0.1700
Data Index: 3886592 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0467. Min Act: -0.1700
Data Index: 7240236 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0467. Min Act: -0.1700
Data Index: 6930463 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0154. Min Act: -0.1700
Data Index: 3531164 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.0154. Min Act: -0.1700
Data Index: 2938032 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9842. Min Act: -0.1700
Data Index: 3041680 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 7116207 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1699
Data Index: 6077368 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 5777743 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 5700052 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9842. Min Act: -0.1700
Data Index: 5503722 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 4237475 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 3930157 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.9529. Min Act: -0.1700
Data Index: 5433750 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19