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

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

Neuron 542 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.6136. Min Act: -0.0000

Data Index: 257797 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.6152. Min Act: -0.0001

Data Index: 1062533 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.5936. Min Act: -0.0001

Data Index: 970292 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.5825. Min Act: -0.0000

Data Index: 1269739 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2248. Min Act: -0.0000

Data Index: 498149 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2812. Min Act: -0.0001

Data Index: 434022 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2576. Min Act: -0.0000

Data Index: 216302 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2339. Min Act: -0.0001

Data Index: 729428 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.3282. Min Act: -0.0000

Data Index: 1278787 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.1559. Min Act: -0.0001

Data Index: 867106 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.1459. Min Act: -0.0001

Data Index: 779914 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2918. Min Act: -0.0000

Data Index: 92045 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.1511. Min Act: -0.0000

Data Index: 767558 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 2.6152. Min Range: -2.6152

Max Act: 1.9189. Min Act: -0.0001

Data Index: 381676 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.2289. Min Act: -0.0000

Data Index: 238453 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 2.6152. Min Range: -2.6152

Max Act: 1.9942. Min Act: -0.0000

Data Index: 853921 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.6152. Min Range: -2.6152

Max Act: 2.1548. Min Act: -0.0001

Data Index: 227470 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 2.6152. Min Range: -2.6152

Max Act: 1.9362. Min Act: -0.0000

Data Index: 828988 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 2.6152. Min Range: -2.6152

Max Act: 1.7897. Min Act: -0.0001

Data Index: 691306 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.6152. Min Range: -2.6152

Max Act: 1.8805. Min Act: -0.0000

Data Index: 615311 (C4 (Web Text))

Max Activating Token Index: 782