Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.3357. Min Act: -0.1700
Data Index: 5338593 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6731451 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.1482. Min Act: -0.1700
Data Index: 1652233 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.1169. Min Act: -0.1700
Data Index: 3967537 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.1169. Min Act: -0.1700
Data Index: 5837721 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.1169. Min Act: -0.1700
Data Index: 7646107 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0857. Min Act: -0.1700
Data Index: 5189098 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0857. Min Act: -0.1700
Data Index: 7449520 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0544. Min Act: -0.1700
Data Index: 1665550 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3091494 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6742104 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9919. Min Act: -0.1700
Data Index: 1046024 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0232. Min Act: -0.1700
Data Index: 4600832 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3357. Min Range: -5.3357
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6488309 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9919. Min Act: -0.1700
Data Index: 8607409 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9919. Min Act: -0.1700
Data Index: 149910 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9294. Min Act: -0.1700
Data Index: 2731328 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9607. Min Act: -0.1700
Data Index: 3206548 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9607. Min Act: -0.1700
Data Index: 3395882 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3357. Min Range: -5.3357
Max Act: 4.9607. Min Act: -0.1700
Data Index: 5839686 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19