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

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

Neuron 1976 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: 3.3959. Min Range: -3.3959

Max Act: 3.2011. Min Act: -0.0000

Data Index: 811207 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.3959. Min Act: -0.0000

Data Index: 673550 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.3221. Min Act: -0.0000

Data Index: 748615 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.1227. Min Act: -0.0000

Data Index: 117120 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.0926. Min Act: -0.0000

Data Index: 1421155 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.2176. Min Act: -0.0000

Data Index: 1350536 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.0546. Min Act: -0.0000

Data Index: 359233 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.9044. Min Act: -0.0000

Data Index: 341315 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.0206. Min Act: -0.0000

Data Index: 65546 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.1546. Min Act: -0.0000

Data Index: 888229 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.8769. Min Act: -0.0000

Data Index: 1320741 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.1214. Min Act: -0.0000

Data Index: 1412825 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.8332. Min Act: -0.0000

Data Index: 367361 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.9650. Min Act: -0.0000

Data Index: 394609 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.8282. Min Act: -0.0000

Data Index: 1151943 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.9404. Min Act: -0.0000

Data Index: 821044 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.3959. Min Range: -3.3959

Max Act: 3.0781. Min Act: -0.0000

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.9185. Min Act: -0.0000

Data Index: 1291124 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.8957. Min Act: -0.0000

Data Index: 270436 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 3.3959. Min Range: -3.3959

Max Act: 2.8832. Min Act: -0.0000

Data Index: 1091553 (C4 (Web Text))

Max Activating Token Index: 534