Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.4738. Min Act: -0.1700
Data Index: 68434 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.4113. Min Act: -0.1700
Data Index: 50300 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2097818 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.3176. Min Act: -0.1700
Data Index: 1415769 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.2551. Min Act: -0.1700
Data Index: 5857539 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.2551. Min Act: -0.1700
Data Index: 6379688 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.2238. Min Act: -0.1700
Data Index: 12776 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1926. Min Act: -0.1700
Data Index: 5194982 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.2238. Min Act: -0.1700
Data Index: 2663507 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1926. Min Act: -0.1699
Data Index: 8645180 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1301. Min Act: -0.1700
Data Index: 5772182 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1301. Min Act: -0.1700
Data Index: 6726538 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1301. Min Act: -0.1700
Data Index: 6577699 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1613. Min Act: -0.1700
Data Index: 6979153 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1301. Min Act: -0.1700
Data Index: 4369313 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.0988. Min Act: -0.1700
Data Index: 2291583 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.1301. Min Act: -0.1700
Data Index: 7998058 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.0988. Min Act: -0.1700
Data Index: 7167269 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.0988. Min Act: -0.1700
Data Index: 5843872 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4738. Min Range: -5.4738
Max Act: 5.0676. Min Act: -0.1700
Data Index: 6820997 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19