Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.6768. Min Act: -0.1700
Data Index: 4424398 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.6608. Min Act: -0.1700
Data Index: 3751942 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.6448. Min Act: -0.1700
Data Index: 3010623 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5965. Min Act: -0.1700
Data Index: 1849767 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5643. Min Act: -0.1700
Data Index: 775990 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5643. Min Act: -0.1700
Data Index: 8138130 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5482. Min Act: -0.1700
Data Index: 1750353 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5482. Min Act: -0.1700
Data Index: 4055116 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5320. Min Act: -0.1700
Data Index: 462229 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4996. Min Act: -0.1700
Data Index: 3665404 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4834. Min Act: -0.1700
Data Index: 5394050 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4672. Min Act: -0.1700
Data Index: 4215110 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5158. Min Act: -0.1700
Data Index: 6264615 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4996. Min Act: -0.1700
Data Index: 995182 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4996. Min Act: -0.1700
Data Index: 4537669 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.5158. Min Act: -0.1700
Data Index: 6404979 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4834. Min Act: -0.1700
Data Index: 4857344 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4996. Min Act: -0.1700
Data Index: 99726 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4996. Min Act: -0.1700
Data Index: 5689859 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6768. Min Range: -2.6768
Max Act: 2.4672. Min Act: -0.1700
Data Index: 3448289 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19