Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0857. Min Range: -7.0857
Max Act: 7.0857. Min Act: -0.1700
Data Index: 3482572 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.4607. Min Act: -0.1700
Data Index: 2336215 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.3669. Min Act: -0.1700
Data Index: 7041238 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.3357. Min Act: -0.1700
Data Index: 6808971 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.2419. Min Act: -0.1700
Data Index: 4138110 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.2107. Min Act: -0.1700
Data Index: 2366677 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.2107. Min Act: -0.1700
Data Index: 2780116 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.2419. Min Act: -0.1700
Data Index: 6624976 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1794. Min Act: -0.1700
Data Index: 6425664 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 1571421 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 7762457 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 4451625 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 7528897 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 5203197 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 4354551 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 6381088 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 3991846 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1144683 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 3765298 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 6888375 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19