Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 813 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.8301. Min Act: -0.1700
Data Index: 5708473 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.7988. Min Act: -0.1700
Data Index: 4965597 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.6738. Min Act: -0.1700
Data Index: 1339067 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.6426. Min Act: -0.1700
Data Index: 65997 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.6113. Min Act: -0.1700
Data Index: 5394432 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4243366 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7484842 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5488. Min Act: -0.1700
Data Index: 5463615 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 8601045 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5488. Min Act: -0.1700
Data Index: 7548721 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 5404458 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 7886266 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 2294477 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 5237978 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.5176. Min Act: -0.1700
Data Index: 3381448 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.4863. Min Act: -0.1700
Data Index: 8327535 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4788633 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.4863. Min Act: -0.1700
Data Index: 869213 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.4863. Min Act: -0.1700
Data Index: 812583 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8301. Min Range: -5.8301
Max Act: 5.4863. Min Act: -0.1700
Data Index: 7151962 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19