Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.4369. Min Act: -0.1700
Data Index: 1329676 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.4055. Min Act: -0.1700
Data Index: 3903777 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3742. Min Act: -0.1700
Data Index: 5290148 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3899. Min Act: -0.1700
Data Index: 5836898 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3899. Min Act: -0.1700
Data Index: 910685 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3899. Min Act: -0.1700
Data Index: 5836895 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3742. Min Act: -0.1700
Data Index: 5836891 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.3585. Min Act: -0.1700
Data Index: 5534752 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2957. Min Act: -0.1700
Data Index: 6116323 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2800. Min Act: -0.1700
Data Index: 4339552 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2800. Min Act: -0.1700
Data Index: 4442704 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2643. Min Act: -0.1700
Data Index: 7881851 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2643. Min Act: -0.1700
Data Index: 4339568 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2329. Min Act: -0.1700
Data Index: 3100089 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2329. Min Act: -0.1700
Data Index: 2534692 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2172. Min Act: -0.1700
Data Index: 4107630 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2172. Min Act: -0.1700
Data Index: 3799170 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2015. Min Act: -0.1700
Data Index: 3056083 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.2015. Min Act: -0.1700
Data Index: 1709422 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.1857. Min Act: -0.1700
Data Index: 402619 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19