Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 771 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1909. Min Range: -3.1909
Max Act: 3.1909. Min Act: -0.1700
Data Index: 6071908 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1909. Min Range: -3.1909
Max Act: 3.1909. Min Act: -0.1700
Data Index: 6902577 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1909. Min Range: -3.1909
Max Act: 3.1437. Min Act: -0.1700
Data Index: 8568611 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1909. Min Range: -3.1909
Max Act: 3.0965. Min Act: -0.1700
Data Index: 4514780 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1909. Min Range: -3.1909
Max Act: 3.0018. Min Act: -0.1700
Data Index: 8568612 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9543. Min Act: -0.1700
Data Index: 4572780 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9860. Min Act: -0.1700
Data Index: 4624496 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9860. Min Act: -0.1700
Data Index: 5181581 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9702. Min Act: -0.1700
Data Index: 2418967 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9385. Min Act: -0.1700
Data Index: 3679006 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9385. Min Act: -0.1700
Data Index: 1324708 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9543. Min Act: -0.1700
Data Index: 2334671 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9543. Min Act: -0.1700
Data Index: 8260558 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9227. Min Act: -0.1700
Data Index: 7245119 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9227. Min Act: -0.1700
Data Index: 3928822 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9068. Min Act: -0.1700
Data Index: 5817578 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9227. Min Act: -0.1700
Data Index: 7513935 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.8910. Min Act: -0.1700
Data Index: 7074795 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.9068. Min Act: -0.1700
Data Index: 4501231 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1909. Min Range: -3.1909
Max Act: 2.8751. Min Act: -0.1700
Data Index: 5514577 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19