Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3446. Min Range: -1.3446

Max Act: 1.2754. Min Act: -0.0000

Data Index: 210641 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.3446. Min Range: -1.3446

Max Act: 1.3446. Min Act: -0.0000

Data Index: 763946 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.3446. Min Range: -1.3446

Max Act: 1.1083. Min Act: -0.0000

Data Index: 547384 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.9329. Min Act: -0.0000

Data Index: 316971 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1096226 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.8593. Min Act: -0.0000

Data Index: 835296 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.7549. Min Act: -0.0000

Data Index: 218277 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.7419. Min Act: -0.0000

Data Index: 317268 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6418. Min Act: -0.0000

Data Index: 586402 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1244681 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1106790 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6868. Min Act: -0.0000

Data Index: 821914 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1386402 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.5437. Min Act: -0.0000

Data Index: 34452 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6213. Min Act: -0.0000

Data Index: 668127 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1119239 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.5758. Min Act: -0.0000

Data Index: 158138 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6338. Min Act: -0.0000

Data Index: 175538 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.5146. Min Act: -0.0000

Data Index: 119528 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.3446. Min Range: -1.3446

Max Act: 0.6216. Min Act: -0.0000

Data Index: 324025 (C4 (Web Text))

Max Activating Token Index: 839