Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.7674. Min Act: -0.1700
Data Index: 6339216 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.4236. Min Act: -0.1700
Data Index: 4335960 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.3924. Min Act: -0.1700
Data Index: 7937442 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.3924. Min Act: -0.1700
Data Index: 3884350 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2986. Min Act: -0.1700
Data Index: 8773877 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2986. Min Act: -0.1700
Data Index: 1387730 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2674. Min Act: -0.1700
Data Index: 7829566 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2986. Min Act: -0.1700
Data Index: 3324468 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2674. Min Act: -0.1700
Data Index: 7607684 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2674. Min Act: -0.1700
Data Index: 6260497 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2986. Min Act: -0.1700
Data Index: 2718992 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2361. Min Act: -0.1700
Data Index: 8611670 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.2049. Min Act: -0.1700
Data Index: 5470085 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1736. Min Act: -0.1700
Data Index: 2242977 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1736. Min Act: -0.1700
Data Index: 6883554 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1111. Min Act: -0.1700
Data Index: 5604310 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1736. Min Act: -0.1700
Data Index: 2953447 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1111. Min Act: -0.1700
Data Index: 8073675 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1424. Min Act: -0.1700
Data Index: 7446645 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7674. Min Range: -7.7674
Max Act: 7.1111. Min Act: -0.1700
Data Index: 3525609 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19