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

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

Neuron 125 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1230809 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2567. Min Act: -0.0000

Data Index: 465113 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1011565 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2605. Min Act: -0.0000

Data Index: 946684 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1256683 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2385. Min Act: -0.0000

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2419. Min Act: -0.0000

Data Index: 496778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2246. Min Act: -0.0000

Data Index: 77471 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2251. Min Act: -0.0000

Data Index: 445027 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1058949 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1064630 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1214388 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2058. Min Act: -0.0000

Data Index: 159096 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2096. Min Act: -0.0000

Data Index: 214494 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2106. Min Act: -0.0000

Data Index: 462312 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2301. Min Act: -0.0000

Data Index: 117461 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2075. Min Act: -0.0000

Data Index: 771147 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2296. Min Act: -0.0000

Data Index: 56540 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2309. Min Act: -0.0000

Data Index: 473835 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2043. Min Act: -0.0000

Data Index: 68339 (C4 (Web Text))

Max Activating Token Index: 20