Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.4989. Min Act: -0.1700
Data Index: 4182599 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2636. Min Act: -0.1700
Data Index: 7392060 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2479. Min Act: -0.1700
Data Index: 7360126 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2479. Min Act: -0.1700
Data Index: 4937282 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2322. Min Act: -0.1700
Data Index: 4175194 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2165. Min Act: -0.1700
Data Index: 870792 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2008. Min Act: -0.1700
Data Index: 3143076 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.2008. Min Act: -0.1700
Data Index: 8679929 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1850. Min Act: -0.1700
Data Index: 3858465 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1850. Min Act: -0.1700
Data Index: 1785545 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1850. Min Act: -0.1700
Data Index: 3995432 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1536. Min Act: -0.1700
Data Index: 8133677 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1378. Min Act: -0.1700
Data Index: 8498644 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1536. Min Act: -0.1700
Data Index: 3313037 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1536. Min Act: -0.1700
Data Index: 6198616 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1378. Min Act: -0.1700
Data Index: 7581917 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1378. Min Act: -0.1700
Data Index: 2347465 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1378. Min Act: -0.1700
Data Index: 5889385 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1221. Min Act: -0.1700
Data Index: 2626374 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4989. Min Range: -3.4989
Max Act: 3.1063. Min Act: -0.1700
Data Index: 4547310 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19