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

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

Neuron 5150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.6138. Min Act: -0.0001

Data Index: 296704 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.3978. Min Act: -0.0001

Data Index: 1108638 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.3937. Min Act: -0.0001

Data Index: 738514 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.2875. Min Act: -0.0001

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.3100. Min Act: -0.0001

Data Index: 488632 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1610766 (Python Code)

Max Activating Token Index: 289

Text #6

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.1761. Min Act: -0.0001

Data Index: 770708 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.1331. Min Act: -0.0000

Data Index: 574752 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.1456. Min Act: -0.0000

Data Index: 936738 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.1826. Min Act: -0.0001

Data Index: 709410 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0719. Min Act: -0.0001

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.1187. Min Act: -0.0001

Data Index: 674903 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0483. Min Act: -0.0001

Data Index: 283174 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0985. Min Act: -0.0001

Data Index: 17423 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.6138. Min Range: -1.6138

Max Act: 0.9937. Min Act: -0.0001

Data Index: 676116 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0778. Min Act: -0.0001

Data Index: 198147 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.6138. Min Range: -1.6138

Max Act: 0.9954. Min Act: -0.0001

Data Index: 903800 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0345. Min Act: -0.0001

Data Index: 309949 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.6138. Min Range: -1.6138

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1541432 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 1.6138. Min Range: -1.6138

Max Act: 1.0392. Min Act: -0.0001

Data Index: 624361 (C4 (Web Text))

Max Activating Token Index: 564