Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1395 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2506. Min Act: -0.1700
Data Index: 6410188 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2340. Min Act: -0.1700
Data Index: 1200894 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2175. Min Act: -0.1700
Data Index: 7719421 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2009. Min Act: -0.1700
Data Index: 3856210 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2009. Min Act: -0.1700
Data Index: 814594 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2009. Min Act: -0.1700
Data Index: 8320610 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 2197547 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1843. Min Act: -0.1700
Data Index: 788750 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.2009. Min Act: -0.1700
Data Index: 4878277 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 1615888 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 8184934 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 4669768 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 4288157 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1510. Min Act: -0.1700
Data Index: 3381293 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1343. Min Act: -0.1700
Data Index: 4272871 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1677. Min Act: -0.1700
Data Index: 5915288 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1176. Min Act: -0.1700
Data Index: 8403085 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1343. Min Act: -0.1700
Data Index: 5774635 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1843. Min Act: -0.1700
Data Index: 941697 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2506. Min Range: -2.2506
Max Act: 2.1176. Min Act: -0.1700
Data Index: 3793422 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19