Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.6321. Min Act: -0.1700
Data Index: 1072655 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.4446. Min Act: -0.1700
Data Index: 4865116 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.3821. Min Act: -0.1700
Data Index: 2603073 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.3196. Min Act: -0.1700
Data Index: 962412 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.3196. Min Act: -0.1700
Data Index: 7344026 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.2571. Min Act: -0.1700
Data Index: 8270297 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3382304 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.2258. Min Act: -0.1700
Data Index: 515430 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1633. Min Act: -0.1700
Data Index: 1216366 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1321. Min Act: -0.1700
Data Index: 3761916 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1321. Min Act: -0.1700
Data Index: 5415483 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1008. Min Act: -0.1700
Data Index: 2425690 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1008. Min Act: -0.1700
Data Index: 3008466 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.1008. Min Act: -0.1700
Data Index: 3802119 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0696. Min Act: -0.1700
Data Index: 494880 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0696. Min Act: -0.1700
Data Index: 3840616 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0696. Min Act: -0.1700
Data Index: 3953430 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0383. Min Act: -0.1700
Data Index: 768858 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0696. Min Act: -0.1700
Data Index: 3974125 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6321. Min Range: -5.6321
Max Act: 5.0696. Min Act: -0.1700
Data Index: 3761907 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19