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

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

Neuron 5842 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: 4.3128. Min Range: -4.3128

Max Act: 4.3128. Min Act: -0.0000

Data Index: 1208521 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.7495. Min Act: -0.0000

Data Index: 226051 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 4.3128. Min Range: -4.3128

Max Act: 4.1529. Min Act: -0.0000

Data Index: 935278 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.8212. Min Act: -0.0000

Data Index: 1101813 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.4322. Min Act: -0.0000

Data Index: 1144615 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 4.3128. Min Range: -4.3128

Max Act: 4.0299. Min Act: -0.0000

Data Index: 1535598 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.6070. Min Act: -0.0000

Data Index: 781509 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.7863. Min Act: -0.0000

Data Index: 1476001 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.7286. Min Act: -0.0000

Data Index: 368786 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.9904. Min Act: -0.0000

Data Index: 1079728 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.6482. Min Act: -0.0000

Data Index: 559324 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.6244. Min Act: -0.0000

Data Index: 1517160 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.4319. Min Act: -0.0000

Data Index: 801135 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.4188. Min Act: -0.0000

Data Index: 1293428 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.5342. Min Act: -0.0000

Data Index: 1483670 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.3853. Min Act: -0.0000

Data Index: 1296958 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.3822. Min Act: -0.0000

Data Index: 826448 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.5378. Min Act: -0.0000

Data Index: 239558 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.4925. Min Act: -0.0000

Data Index: 492975 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 4.3128. Min Range: -4.3128

Max Act: 3.4935. Min Act: -0.0000

Data Index: 494581 (C4 (Web Text))

Max Activating Token Index: 118