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

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

Neuron 351 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: 0.4412. Min Range: -0.4412

Max Act: 0.4412. Min Act: -0.0000

Data Index: 314949 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2736. Min Act: -0.0000

Data Index: 701589 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2358. Min Act: -0.0000

Data Index: 768184 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2279. Min Act: -0.0000

Data Index: 538251 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2197. Min Act: -0.0000

Data Index: 339643 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2244. Min Act: -0.0000

Data Index: 419665 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2145. Min Act: -0.0000

Data Index: 798171 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2165. Min Act: -0.0000

Data Index: 403902 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2151. Min Act: -0.0000

Data Index: 259992 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2150. Min Act: -0.0000

Data Index: 565920 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2107. Min Act: -0.0000

Data Index: 881239 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1182663 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1922. Min Act: -0.0000

Data Index: 78722 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1327954 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1206081 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1818. Min Act: -0.0000

Data Index: 53644 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1660. Min Act: -0.0000

Data Index: 148 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1758. Min Act: -0.0000

Data Index: 473180 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1691. Min Act: -0.0000

Data Index: 589522 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1290473 (C4 (Web Text))

Max Activating Token Index: 205