Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5908 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.7621. Min Act: -0.1700
Data Index: 4624313 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.7309. Min Act: -0.1700
Data Index: 485239 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6684. Min Act: -0.1700
Data Index: 1139526 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6684. Min Act: -0.1699
Data Index: 1744346 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6371. Min Act: -0.1700
Data Index: 7125847 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6371. Min Act: -0.1700
Data Index: 3991262 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 4560426 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6059. Min Act: -0.1700
Data Index: 8400551 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 992727 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 2246056 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 815669 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 4859780 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 7102871 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 4464576 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 7553798 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 723802 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 6347542 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5746. Min Act: -0.1700
Data Index: 2402197 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 5774640 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.5434. Min Act: -0.1700
Data Index: 5338123 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19