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

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

Neuron 3809 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: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 277134 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2540. Min Act: -0.0001

Data Index: 849989 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2383. Min Act: -0.0001

Data Index: 947532 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2555. Min Act: -0.0001

Data Index: 242106 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2526. Min Act: -0.0001

Data Index: 305240 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2442. Min Act: -0.0001

Data Index: 417858 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2422. Min Act: -0.0001

Data Index: 272054 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1190182 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2314. Min Act: -0.0001

Data Index: 884535 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2366. Min Act: -0.0001

Data Index: 150829 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2296. Min Act: -0.0001

Data Index: 416102 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2374. Min Act: -0.0001

Data Index: 394578 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2379. Min Act: -0.0001

Data Index: 431145 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2350. Min Act: -0.0001

Data Index: 388971 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1287035 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2330. Min Act: -0.0001

Data Index: 315460 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2304. Min Act: -0.0001

Data Index: 607628 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1261859 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1096042 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2441. Min Act: -0.0001

Data Index: 388870 (C4 (Web Text))

Max Activating Token Index: 672