Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.2578. Min Act: -0.1700
Data Index: 289925 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.2578. Min Act: -0.1700
Data Index: 4087107 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.2890. Min Act: -0.1700
Data Index: 6528254 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.2265. Min Act: -0.1700
Data Index: 8795639 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.1328. Min Act: -0.1700
Data Index: 3696645 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1906516 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.1015. Min Act: -0.1700
Data Index: 5992741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2890. Min Range: -6.2890
Max Act: 6.0390. Min Act: -0.1700
Data Index: 384466 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.9765. Min Act: -0.1700
Data Index: 8628157 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3770832 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.9453. Min Act: -0.1700
Data Index: 289924 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.8203. Min Act: -0.1700
Data Index: 3826313 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 1704687 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 2124679 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.6953. Min Act: -0.1700
Data Index: 2547105 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.6953. Min Act: -0.1700
Data Index: 730631 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.7265. Min Act: -0.1700
Data Index: 7650878 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.6640. Min Act: -0.1700
Data Index: 2057393 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.6328. Min Act: -0.1700
Data Index: 3854585 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2890. Min Range: -6.2890
Max Act: 5.6328. Min Act: -0.1700
Data Index: 111018 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19