Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.8321. Min Act: -0.1700
Data Index: 620736 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7696. Min Act: -0.1700
Data Index: 4492243 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7696. Min Act: -0.1700
Data Index: 946264 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7384. Min Act: -0.1700
Data Index: 1266199 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7071. Min Act: -0.1700
Data Index: 789867 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6759. Min Act: -0.1700
Data Index: 2031819 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6759. Min Act: -0.1700
Data Index: 8734391 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6759. Min Act: -0.1700
Data Index: 3797103 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6446. Min Act: -0.1700
Data Index: 4469329 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6446. Min Act: -0.1700
Data Index: 4858972 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6134. Min Act: -0.1700
Data Index: 7843726 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6134. Min Act: -0.1700
Data Index: 1433282 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.5509. Min Act: -0.1700
Data Index: 3363573 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.5196. Min Act: -0.1700
Data Index: 2276985 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.5196. Min Act: -0.1700
Data Index: 4357775 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.4571. Min Act: -0.1700
Data Index: 4405489 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.4884. Min Act: -0.1700
Data Index: 6512872 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.4884. Min Act: -0.1700
Data Index: 587576 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.4571. Min Act: -0.1700
Data Index: 7622330 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.4884. Min Act: -0.1700
Data Index: 3529724 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19