Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.4335. Min Act: -0.1700
Data Index: 397583 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2147. Min Act: -0.1700
Data Index: 5372433 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9960. Min Act: -0.1700
Data Index: 6290971 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9960. Min Act: -0.1700
Data Index: 3225675 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9960. Min Act: -0.1700
Data Index: 3120791 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9647. Min Act: -0.1700
Data Index: 7816360 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9647. Min Act: -0.1700
Data Index: 4684703 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9647. Min Act: -0.1700
Data Index: 3011277 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9022. Min Act: -0.1700
Data Index: 5237410 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9022. Min Act: -0.1700
Data Index: 6798206 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9022. Min Act: -0.1700
Data Index: 7359257 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.9022. Min Act: -0.1700
Data Index: 7671069 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 5831195 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 422688 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 972949 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8710. Min Act: -0.1700
Data Index: 6677893 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 7629774 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 6571571 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 4303720 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4335. Min Range: -5.4335
Max Act: 4.8397. Min Act: -0.1700
Data Index: 4302647 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19