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

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

Neuron 2299 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: 0.3112. Min Range: -0.3112

Max Act: 0.3112. Min Act: -0.0001

Data Index: 363795 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1330626 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2789. Min Act: -0.0001

Data Index: 888080 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2639. Min Act: -0.0001

Data Index: 980561 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1324187 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1009690 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2548. Min Act: -0.0001

Data Index: 177819 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2323. Min Act: -0.0001

Data Index: 199766 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2403. Min Act: -0.0001

Data Index: 829495 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2468. Min Act: -0.0001

Data Index: 931224 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2390. Min Act: -0.0001

Data Index: 976220 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2342. Min Act: -0.0001

Data Index: 20596 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2364. Min Act: -0.0001

Data Index: 908746 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2379. Min Act: -0.0001

Data Index: 107977 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2355. Min Act: -0.0001

Data Index: 818225 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2188. Min Act: -0.0001

Data Index: 787070 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2262. Min Act: -0.0001

Data Index: 495552 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2157. Min Act: -0.0001

Data Index: 374496 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2087. Min Act: -0.0001

Data Index: 1002096 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1103842 (C4 (Web Text))

Max Activating Token Index: 358