Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 319 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5660. Min Act: -0.0001

Data Index: 316226 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5399. Min Act: -0.0001

Data Index: 758438 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2724. Min Act: -0.0001

Data Index: 812560 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5168. Min Act: -0.0001

Data Index: 1206154 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.3049. Min Act: -0.0001

Data Index: 60450 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.3392. Min Act: -0.0001

Data Index: 714882 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.3770. Min Act: -0.0001

Data Index: 1273967 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.4195. Min Act: -0.0001

Data Index: 1187108 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2973. Min Act: -0.0001

Data Index: 211409 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.3225. Min Act: -0.0001

Data Index: 530218 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2655. Min Act: -0.0001

Data Index: 1018175 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1229. Min Act: -0.0001

Data Index: 1447955 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2567. Min Act: -0.0001

Data Index: 534162 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.3688. Min Act: -0.0001

Data Index: 1327193 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1745. Min Act: -0.0001

Data Index: 1037371 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2260. Min Act: -0.0001

Data Index: 1442903 (Python Code)

Max Activating Token Index: 986

Text #16

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1295. Min Act: -0.0001

Data Index: 97526 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1963. Min Act: -0.0001

Data Index: 653869 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2536. Min Act: -0.0001

Data Index: 373973 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2164. Min Act: -0.0001

Data Index: 1594120 (Python Code)

Max Activating Token Index: 62