Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2306. Min Range: -7.2306
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5235776 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2306. Min Range: -7.2306
Max Act: 7.1056. Min Act: -0.1700
Data Index: 3662306 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.9181. Min Act: -0.1700
Data Index: 5123038 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.9493. Min Act: -0.1700
Data Index: 639568 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.9181. Min Act: -0.1700
Data Index: 2690344 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8868. Min Act: -0.1700
Data Index: 786717 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8243. Min Act: -0.1700
Data Index: 2745490 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.7931. Min Act: -0.1700
Data Index: 8039633 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8556. Min Act: -0.1700
Data Index: 2010427 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8243. Min Act: -0.1700
Data Index: 8399385 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8556. Min Act: -0.1700
Data Index: 6751535 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8243. Min Act: -0.1700
Data Index: 5782183 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.7931. Min Act: -0.1700
Data Index: 1210036 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.8243. Min Act: -0.1700
Data Index: 7868995 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.7618. Min Act: -0.1700
Data Index: 4322611 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.6993. Min Act: -0.1700
Data Index: 73560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2800699 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.6993. Min Act: -0.1700
Data Index: 6148223 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.7931. Min Act: -0.1700
Data Index: 8423038 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2306. Min Range: -7.2306
Max Act: 6.7306. Min Act: -0.1700
Data Index: 7773570 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19