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

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

Neuron 5121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1383010 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1436281 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1542087 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1458460 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1574581 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3707. Min Act: -0.0000

Data Index: 230594 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3483. Min Act: -0.0000

Data Index: 927674 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3489. Min Act: -0.0000

Data Index: 668128 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1530895 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1096075 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3586. Min Act: -0.0000

Data Index: 721267 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3582. Min Act: -0.0000

Data Index: 526526 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3301. Min Act: -0.0000

Data Index: 528511 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1142730 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1427023 (Python Code)

Max Activating Token Index: 511

Text #15

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1299775 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1133593 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3322. Min Act: -0.0000

Data Index: 412446 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3385. Min Act: -0.0000

Data Index: 714795 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.3360. Min Act: -0.0000

Data Index: 870281 (C4 (Web Text))

Max Activating Token Index: 940