Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 635 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8324. Min Range: -7.8324
Max Act: 7.8324. Min Act: -0.1700
Data Index: 7554594 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8324. Min Range: -7.8324
Max Act: 7.1137. Min Act: -0.1700
Data Index: 750298 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.9574. Min Act: -0.1700
Data Index: 5980538 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.9574. Min Act: -0.1700
Data Index: 615267 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.8949. Min Act: -0.1700
Data Index: 2874797 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.8012. Min Act: -0.1700
Data Index: 6273416 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.8012. Min Act: -0.1700
Data Index: 5924148 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.8012. Min Act: -0.1700
Data Index: 1662586 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.7699. Min Act: -0.1700
Data Index: 1008376 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.7699. Min Act: -0.1700
Data Index: 8745427 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.7387. Min Act: -0.1700
Data Index: 2274220 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.6762. Min Act: -0.1700
Data Index: 2987395 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7755104 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.6137. Min Act: -0.1700
Data Index: 2848034 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5824. Min Act: -0.1700
Data Index: 1112624 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5824. Min Act: -0.1700
Data Index: 5474026 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5824. Min Act: -0.1700
Data Index: 4885932 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5512. Min Act: -0.1700
Data Index: 5780374 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5199. Min Act: -0.1700
Data Index: 6300506 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8324. Min Range: -7.8324
Max Act: 6.5199. Min Act: -0.1700
Data Index: 5521011 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19