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

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

Neuron 1791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2350. Min Act: -0.0001

Data Index: 476808 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2472. Min Act: -0.0001

Data Index: 310593 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2364. Min Act: -0.0001

Data Index: 1187922 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2307. Min Act: -0.0001

Data Index: 565076 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1084495 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1172111 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1808. Min Act: -0.0001

Data Index: 159090 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1261991 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2021. Min Act: -0.0001

Data Index: 233401 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1018020 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1889. Min Act: -0.0001

Data Index: 287613 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1931. Min Act: -0.0001

Data Index: 979521 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1873. Min Act: -0.0001

Data Index: 796074 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1994. Min Act: -0.0001

Data Index: 966540 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2060. Min Act: -0.0001

Data Index: 569184 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1152704 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1860. Min Act: -0.0001

Data Index: 386846 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1895. Min Act: -0.0001

Data Index: 662565 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1822. Min Act: -0.0001

Data Index: 358067 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1026489 (C4 (Web Text))

Max Activating Token Index: 191