Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.5708. Min Act: -0.1700
Data Index: 4958267 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.5083. Min Act: -0.1700
Data Index: 1478276 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.3833. Min Act: -0.1700
Data Index: 1545462 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.3208. Min Act: -0.1700
Data Index: 5692790 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.1645. Min Act: -0.1700
Data Index: 3684403 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.1958. Min Act: -0.1700
Data Index: 6645349 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.1645. Min Act: -0.1700
Data Index: 2247731 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.0395. Min Act: -0.1700
Data Index: 702467 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5708. Min Range: -8.5708
Max Act: 8.0083. Min Act: -0.1700
Data Index: 1086502 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.9770. Min Act: -0.1700
Data Index: 1287965 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.9770. Min Act: -0.1700
Data Index: 4997013 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.9458. Min Act: -0.1700
Data Index: 1654291 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.9458. Min Act: -0.1700
Data Index: 4446397 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.9145. Min Act: -0.1700
Data Index: 688097 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.8208. Min Act: -0.1700
Data Index: 8600542 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.8208. Min Act: -0.1700
Data Index: 7727195 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.8520. Min Act: -0.1700
Data Index: 4661370 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.7895. Min Act: -0.1700
Data Index: 6780121 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.7895. Min Act: -0.1700
Data Index: 1661280 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5708. Min Range: -8.5708
Max Act: 7.7583. Min Act: -0.1700
Data Index: 7326085 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19