Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1124905 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3435. Min Act: -0.0000

Data Index: 751623 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2978. Min Act: -0.0000

Data Index: 700473 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1568919 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2665. Min Act: -0.0000

Data Index: 561446 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1002399 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2775. Min Act: -0.0000

Data Index: 886310 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1653396 (Python Code)

Max Activating Token Index: 933

Text #8

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1518299 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2244. Min Act: -0.0000

Data Index: 299298 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1001858 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1641239 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1472400 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2197. Min Act: -0.0000

Data Index: 334586 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1179724 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1305113 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1359151 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2180. Min Act: -0.0000

Data Index: 988323 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1303773 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1580697 (Python Code)

Max Activating Token Index: 554