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

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

Neuron 4988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2496. Min Range: -4.2496

Max Act: 4.2496. Min Act: -0.0000

Data Index: 191097 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.5747. Min Act: -0.0000

Data Index: 685458 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.8280. Min Act: -0.0000

Data Index: 1008568 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.3425. Min Act: -0.0000

Data Index: 980224 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.4217. Min Act: -0.0000

Data Index: 326125 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2190. Min Act: -0.0000

Data Index: 1293236 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.0474. Min Act: -0.0000

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.0226. Min Act: -0.0000

Data Index: 341201 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2894. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1155174 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 4.2496. Min Range: -4.2496

Max Act: 2.9551. Min Act: -0.0000

Data Index: 771843 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2542. Min Act: -0.0000

Data Index: 1329415 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.1152. Min Act: -0.0000

Data Index: 743592 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.0912. Min Act: -0.0000

Data Index: 296416 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2262. Min Act: -0.0000

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.0766. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.3763. Min Act: -0.0000

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2553. Min Act: -0.0000

Data Index: 385320 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.2009. Min Act: -0.0000

Data Index: 556972 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 4.2496. Min Range: -4.2496

Max Act: 3.3230. Min Act: -0.0000

Data Index: 573616 (C4 (Web Text))

Max Activating Token Index: 265