Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.4180. Min Act: -0.0000

Data Index: 453200 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.2582. Min Act: -0.0000

Data Index: 71217 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.2553. Min Act: -0.0000

Data Index: 514976 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.2042. Min Act: -0.0000

Data Index: 618031 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.2034. Min Act: -0.0000

Data Index: 1019831 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.1709. Min Act: -0.0000

Data Index: 1153231 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.1781. Min Act: -0.0000

Data Index: 754296 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.1682. Min Act: -0.0000

Data Index: 972153 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.1168. Min Act: -0.0000

Data Index: 259754 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.0901. Min Act: -0.0000

Data Index: 149305 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.0238. Min Act: -0.0000

Data Index: 1114256 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.0424. Min Act: -0.0000

Data Index: 472442 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.9359. Min Act: -0.0000

Data Index: 528027 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 2.4180. Min Range: -2.4180

Max Act: 2.0214. Min Act: -0.0000

Data Index: 664634 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.8542. Min Act: -0.0000

Data Index: 22971 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.9300. Min Act: -0.0000

Data Index: 21976 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.9086. Min Act: -0.0000

Data Index: 750947 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.8138. Min Act: -0.0000

Data Index: 335606 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.8865. Min Act: -0.0000

Data Index: 20272 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 2.4180. Min Range: -2.4180

Max Act: 1.9802. Min Act: -0.0000

Data Index: 107812 (C4 (Web Text))

Max Activating Token Index: 32