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

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

Neuron 444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2483. Min Range: -4.2483

Max Act: 4.2483. Min Act: -0.0001

Data Index: 610512 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.9193. Min Act: -0.0001

Data Index: 947467 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.6518. Min Act: -0.0001

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.6444. Min Act: -0.0001

Data Index: 447200 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.3387. Min Act: -0.0000

Data Index: 75608 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.4599. Min Act: -0.0001

Data Index: 840449 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.3406. Min Act: -0.0000

Data Index: 1341037 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.3243. Min Act: -0.0001

Data Index: 606054 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.4538. Min Act: -0.0001

Data Index: 1338301 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.2487. Min Act: -0.0000

Data Index: 926887 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.2648. Min Act: -0.0001

Data Index: 118087 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.2593. Min Act: -0.0001

Data Index: 461198 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 4.2483. Min Range: -4.2483

Max Act: 2.9175. Min Act: -0.0000

Data Index: 456134 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.2178. Min Act: -0.0001

Data Index: 399761 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.0623. Min Act: -0.0000

Data Index: 707369 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.1755. Min Act: -0.0000

Data Index: 32893 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.1960. Min Act: -0.0001

Data Index: 872115 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.1623. Min Act: -0.0001

Data Index: 132375 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.3004. Min Act: -0.0000

Data Index: 854615 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 4.2483. Min Range: -4.2483

Max Act: 3.1562. Min Act: -0.0001

Data Index: 1316026 (C4 (Web Text))

Max Activating Token Index: 851