Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1370 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1158. Min Range: -6.1158
Max Act: 6.1158. Min Act: -0.1700
Data Index: 6641806 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.8658. Min Act: -0.1700
Data Index: 3595751 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.7408. Min Act: -0.1700
Data Index: 7015804 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.7408. Min Act: -0.1700
Data Index: 1514283 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.7096. Min Act: -0.1700
Data Index: 5042937 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.7096. Min Act: -0.1700
Data Index: 7685940 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4208888 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.6783. Min Act: -0.1700
Data Index: 4470903 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.6471. Min Act: -0.1700
Data Index: 2746741 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.6158. Min Act: -0.1700
Data Index: 1178308 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5846. Min Act: -0.1700
Data Index: 1000579 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.6158. Min Act: -0.1700
Data Index: 2269180 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.6158. Min Act: -0.1700
Data Index: 8274951 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5846. Min Act: -0.1700
Data Index: 397439 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5846. Min Act: -0.1700
Data Index: 6624586 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5846. Min Act: -0.1700
Data Index: 7688285 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5533. Min Act: -0.1700
Data Index: 5841340 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5846. Min Act: -0.1700
Data Index: 5394542 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5533. Min Act: -0.1700
Data Index: 5020578 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1158. Min Range: -6.1158
Max Act: 5.5533. Min Act: -0.1700
Data Index: 1199676 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19