Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.3595. Min Act: -0.1700
Data Index: 1622348 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.2970. Min Act: -0.1700
Data Index: 3133515 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.2970. Min Act: -0.1700
Data Index: 2766260 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.1720. Min Act: -0.1700
Data Index: 3607973 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.1720. Min Act: -0.1700
Data Index: 3160504 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.1095. Min Act: -0.1700
Data Index: 7646919 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.0783. Min Act: -0.1700
Data Index: 6503011 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.0783. Min Act: -0.1700
Data Index: 759128 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3595. Min Range: -8.3595
Max Act: 8.0158. Min Act: -0.1700
Data Index: 4900859 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.9220. Min Act: -0.1700
Data Index: 3087411 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.8908. Min Act: -0.1700
Data Index: 6433946 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.8908. Min Act: -0.1700
Data Index: 5158853 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.8283. Min Act: -0.1700
Data Index: 3625530 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.7970. Min Act: -0.1700
Data Index: 2148494 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.8283. Min Act: -0.1700
Data Index: 3286154 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.7658. Min Act: -0.1700
Data Index: 6643787 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.7658. Min Act: -0.1700
Data Index: 6238200 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.7345. Min Act: -0.1700
Data Index: 2695977 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.7033. Min Act: -0.1700
Data Index: 6067998 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3595. Min Range: -8.3595
Max Act: 7.6408. Min Act: -0.1700
Data Index: 882007 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19