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

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

Neuron 4154 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1207. Min Range: -5.1207

Max Act: 5.1207. Min Act: -0.0000

Data Index: 480959 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.9187. Min Act: -0.0001

Data Index: 187106 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.9838. Min Act: -0.0000

Data Index: 392755 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.6272. Min Act: -0.0000

Data Index: 268490 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.9242. Min Act: -0.0001

Data Index: 890841 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.7277. Min Act: -0.0001

Data Index: 82879 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.6440. Min Act: -0.0001

Data Index: 974515 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.4350. Min Act: -0.0001

Data Index: 464902 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.5333. Min Act: -0.0001

Data Index: 1002656 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.3243. Min Act: -0.0000

Data Index: 1301609 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.7520. Min Act: -0.0001

Data Index: 974415 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.1275. Min Act: -0.0000

Data Index: 173811 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.2453. Min Act: -0.0001

Data Index: 405423 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.2691. Min Act: -0.0000

Data Index: 452288 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 5.1207. Min Range: -5.1207

Max Act: 3.9420. Min Act: -0.0000

Data Index: 686272 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 5.1207. Min Range: -5.1207

Max Act: 4.1695. Min Act: -0.0000

Data Index: 406500 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 5.1207. Min Range: -5.1207

Max Act: 3.7956. Min Act: -0.0000

Data Index: 689328 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 5.1207. Min Range: -5.1207

Max Act: 3.5837. Min Act: -0.0001

Data Index: 1232589 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 5.1207. Min Range: -5.1207

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1349929 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.1207. Min Range: -5.1207

Max Act: 3.6928. Min Act: -0.0000

Data Index: 12867 (C4 (Web Text))

Max Activating Token Index: 273