Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5016 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.5383. Min Act: -0.1700
Data Index: 5061387 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.3508. Min Act: -0.1700
Data Index: 1231368 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2883. Min Act: -0.1700
Data Index: 6072756 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2883. Min Act: -0.1700
Data Index: 8654156 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2571. Min Act: -0.1700
Data Index: 4094764 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2571. Min Act: -0.1700
Data Index: 7711229 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1946. Min Act: -0.1700
Data Index: 3964433 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2258. Min Act: -0.1700
Data Index: 2833156 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2258. Min Act: -0.1700
Data Index: 8545835 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.2258. Min Act: -0.1700
Data Index: 5377997 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1946. Min Act: -0.1700
Data Index: 5285879 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1946. Min Act: -0.1700
Data Index: 4938048 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1633. Min Act: -0.1700
Data Index: 4440132 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1633. Min Act: -0.1700
Data Index: 3532070 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1321. Min Act: -0.1700
Data Index: 1510860 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1321. Min Act: -0.1700
Data Index: 7472091 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.1321. Min Act: -0.1700
Data Index: 7037483 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.0696. Min Act: -0.1700
Data Index: 6580926 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.0696. Min Act: -0.1700
Data Index: 3392056 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5383. Min Range: -7.5383
Max Act: 7.0696. Min Act: -0.1700
Data Index: 1646160 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19