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

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

Neuron 1803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8661. Min Act: -0.0000

Data Index: 1532925 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7586. Min Act: -0.0000

Data Index: 1459924 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.2312. Min Act: -0.0000

Data Index: 1616824 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.5170. Min Act: -0.0000

Data Index: 1564393 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.2629. Min Act: -0.0000

Data Index: 1496780 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9412. Min Act: -0.0000

Data Index: 107471 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.1314. Min Act: -0.0000

Data Index: 1492420 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.0763. Min Act: -0.0000

Data Index: 1633774 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9437. Min Act: -0.0000

Data Index: 1376203 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.0176. Min Act: -0.0000

Data Index: 328170 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9988. Min Act: -0.0000

Data Index: 273233 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.8517. Min Act: -0.0000

Data Index: 1021460 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1392761 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9623. Min Act: -0.0000

Data Index: 552693 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.8066. Min Act: -0.0000

Data Index: 588481 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.0541. Min Act: -0.0000

Data Index: 1506010 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9145. Min Act: -0.0000

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.8836. Min Act: -0.0000

Data Index: 1363333 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.7233. Min Act: -0.0000

Data Index: 1543851 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 3.8661. Min Range: -3.8661

Max Act: 2.9879. Min Act: -0.0000

Data Index: 1082544 (C4 (Web Text))

Max Activating Token Index: 855