Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.8150. Min Act: -0.1700
Data Index: 5825114 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.7838. Min Act: -0.1700
Data Index: 2013202 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.7525. Min Act: -0.1700
Data Index: 8325489 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.7213. Min Act: -0.1700
Data Index: 6846881 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.6900. Min Act: -0.1700
Data Index: 2212094 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.6900. Min Act: -0.1700
Data Index: 961912 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.6588. Min Act: -0.1700
Data Index: 633509 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.6275. Min Act: -0.1700
Data Index: 6740009 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.5338. Min Act: -0.1700
Data Index: 6755721 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.5025. Min Act: -0.1700
Data Index: 672225 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.4713. Min Act: -0.1700
Data Index: 538466 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.4400. Min Act: -0.1700
Data Index: 6107998 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5013881 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5825854 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.3775. Min Act: -0.1700
Data Index: 645058 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.3463. Min Act: -0.1700
Data Index: 8735250 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.3463. Min Act: -0.1700
Data Index: 5488426 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.3150. Min Act: -0.1700
Data Index: 5821656 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.3150. Min Act: -0.1700
Data Index: 6810843 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8150. Min Range: -6.8150
Max Act: 6.2838. Min Act: -0.1700
Data Index: 1504484 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19