Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.9403. Min Act: -0.1700
Data Index: 851639 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.9403. Min Act: -0.1700
Data Index: 6602901 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.8778. Min Act: -0.1700
Data Index: 6503473 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.8465. Min Act: -0.1700
Data Index: 5551918 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.8465. Min Act: -0.1700
Data Index: 3116484 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.8153. Min Act: -0.1700
Data Index: 4849533 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.7528. Min Act: -0.1700
Data Index: 894624 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.7528. Min Act: -0.1700
Data Index: 619211 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8740654 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.6903. Min Act: -0.1700
Data Index: 5231227 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.6590. Min Act: -0.1700
Data Index: 5163715 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.6278. Min Act: -0.1700
Data Index: 3184281 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.6590. Min Act: -0.1700
Data Index: 7754243 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5965. Min Act: -0.1700
Data Index: 2353238 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5965. Min Act: -0.1700
Data Index: 3852770 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5965. Min Act: -0.1700
Data Index: 8369931 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5653. Min Act: -0.1700
Data Index: 3559339 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5653. Min Act: -0.1700
Data Index: 3392194 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5965. Min Act: -0.1700
Data Index: 6919219 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9403. Min Range: -5.9403
Max Act: 5.5653. Min Act: -0.1700
Data Index: 4951909 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19