Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5210. Min Range: -8.5210
Max Act: 8.5210. Min Act: -0.1700
Data Index: 7842318 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5210. Min Range: -8.5210
Max Act: 8.1773. Min Act: -0.1700
Data Index: 2104589 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5210. Min Range: -8.5210
Max Act: 8.1460. Min Act: -0.1700
Data Index: 4365995 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5210. Min Range: -8.5210
Max Act: 8.0210. Min Act: -0.1700
Data Index: 4493357 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.9273. Min Act: -0.1700
Data Index: 2712999 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2181678 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.6773. Min Act: -0.1700
Data Index: 5572245 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.6460. Min Act: -0.1700
Data Index: 1387206 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5897854 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.4585. Min Act: -0.1700
Data Index: 1537291 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3960. Min Act: -0.1700
Data Index: 632816 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3960. Min Act: -0.1700
Data Index: 6220308 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3648. Min Act: -0.1700
Data Index: 2252783 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3335. Min Act: -0.1700
Data Index: 738468 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3648. Min Act: -0.1700
Data Index: 5416705 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3648. Min Act: -0.1700
Data Index: 7671490 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3335. Min Act: -0.1700
Data Index: 4497348 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.2710. Min Act: -0.1700
Data Index: 2439125 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.2398. Min Act: -0.1700
Data Index: 7445164 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5210. Min Range: -8.5210
Max Act: 7.3335. Min Act: -0.1700
Data Index: 2896733 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19