Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3246. Min Range: -9.3246
Max Act: 9.3246. Min Act: -0.1700
Data Index: 5789517 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3246. Min Range: -9.3246
Max Act: 9.0121. Min Act: -0.1700
Data Index: 4309536 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3246. Min Range: -9.3246
Max Act: 9.0121. Min Act: -0.1700
Data Index: 267703 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.9496. Min Act: -0.1700
Data Index: 5289074 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.8246. Min Act: -0.1700
Data Index: 1922117 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.8246. Min Act: -0.1700
Data Index: 8466426 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.8246. Min Act: -0.1700
Data Index: 4087940 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.8246. Min Act: -0.1700
Data Index: 8291702 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.8246. Min Act: -0.1700
Data Index: 3763260 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.6996. Min Act: -0.1700
Data Index: 4635482 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.6996. Min Act: -0.1700
Data Index: 8557017 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.6371. Min Act: -0.1700
Data Index: 7441612 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.6371. Min Act: -0.1700
Data Index: 2082966 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5746. Min Act: -0.1700
Data Index: 2963170 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5746. Min Act: -0.1700
Data Index: 6038114 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5121. Min Act: -0.1700
Data Index: 5906180 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5121. Min Act: -0.1700
Data Index: 7919023 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.4496. Min Act: -0.1700
Data Index: 1449078 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5121. Min Act: -0.1700
Data Index: 1424709 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3246. Min Range: -9.3246
Max Act: 8.5121. Min Act: -0.1700
Data Index: 4255273 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19