Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2883. Min Range: -7.2883
Max Act: 7.2883. Min Act: -0.1700
Data Index: 2550531 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2883. Min Range: -7.2883
Max Act: 7.1321. Min Act: -0.1700
Data Index: 7128004 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2883. Min Range: -7.2883
Max Act: 7.1321. Min Act: -0.1700
Data Index: 4775771 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2883. Min Range: -7.2883
Max Act: 7.0383. Min Act: -0.1700
Data Index: 3309195 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.9758. Min Act: -0.1700
Data Index: 4838146 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.9133. Min Act: -0.1700
Data Index: 3968222 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.9133. Min Act: -0.1700
Data Index: 6102757 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.7883. Min Act: -0.1700
Data Index: 6359610 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.7258. Min Act: -0.1700
Data Index: 6482964 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.7258. Min Act: -0.1700
Data Index: 3435292 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6946. Min Act: -0.1700
Data Index: 817600 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6946. Min Act: -0.1700
Data Index: 4919624 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6633. Min Act: -0.1700
Data Index: 6191675 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6946. Min Act: -0.1700
Data Index: 4741510 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6946. Min Act: -0.1700
Data Index: 5256070 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6633. Min Act: -0.1700
Data Index: 4551786 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6321. Min Act: -0.1700
Data Index: 8120468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6321. Min Act: -0.1700
Data Index: 1002331 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6321. Min Act: -0.1700
Data Index: 1635171 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2883. Min Range: -7.2883
Max Act: 6.6008. Min Act: -0.1700
Data Index: 195742 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19