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

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

Neuron 4191 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.7463. Min Act: -0.0000

Data Index: 232367 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.6493. Min Act: -0.0000

Data Index: 956753 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.5147. Min Act: -0.0000

Data Index: 1201972 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.5140. Min Act: -0.0000

Data Index: 1330726 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.4192. Min Act: -0.0000

Data Index: 496801 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1144318 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.4039. Min Act: -0.0000

Data Index: 313567 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.5234. Min Act: -0.0000

Data Index: 235554 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.5309. Min Act: -0.0000

Data Index: 182107 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3225. Min Act: -0.0000

Data Index: 312426 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3556. Min Act: -0.0000

Data Index: 723249 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3625. Min Act: -0.0000

Data Index: 442889 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3328. Min Act: -0.0000

Data Index: 710497 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3386. Min Act: -0.0000

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3325. Min Act: -0.0000

Data Index: 207660 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3403. Min Act: -0.0000

Data Index: 36138 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3545. Min Act: -0.0000

Data Index: 1255250 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3236. Min Act: -0.0000

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.3808. Min Act: -0.0000

Data Index: 105860 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 2.7463. Min Range: -2.7463

Max Act: 2.2103. Min Act: -0.0000

Data Index: 683754 (C4 (Web Text))

Max Activating Token Index: 743