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

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

Neuron 4285 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.2205. Min Act: -0.0001

Data Index: 337688 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.1989. Min Act: -0.0001

Data Index: 313265 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.1746. Min Act: -0.0001

Data Index: 295241 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8769. Min Act: -0.0001

Data Index: 972145 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9501. Min Act: -0.0001

Data Index: 556469 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9330. Min Act: -0.0001

Data Index: 301722 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1281676 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1319387 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9479. Min Act: -0.0001

Data Index: 673845 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1092536 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9378. Min Act: -0.0001

Data Index: 921090 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9392. Min Act: -0.0001

Data Index: 693311 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9455. Min Act: -0.0001

Data Index: 691915 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8592. Min Act: -0.0001

Data Index: 526776 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9598. Min Act: -0.0001

Data Index: 896979 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9442. Min Act: -0.0001

Data Index: 274466 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9640. Min Act: -0.0001

Data Index: 865900 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8376. Min Act: -0.0001

Data Index: 296465 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7858. Min Act: -0.0001

Data Index: 543924 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8620. Min Act: -0.0001

Data Index: 314222 (C4 (Web Text))

Max Activating Token Index: 840