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

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

Neuron 2754 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.7348. Min Act: -0.0000

Data Index: 865075 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.7113. Min Act: -0.0000

Data Index: 233123 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.5835. Min Act: -0.0000

Data Index: 232916 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3707. Min Act: -0.0000

Data Index: 492952 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1068723 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.2725. Min Act: -0.0000

Data Index: 382671 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.2225. Min Act: -0.0000

Data Index: 122389 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.1335. Min Act: -0.0000

Data Index: 113468 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.1321. Min Act: -0.0000

Data Index: 979316 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1020263 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.1491. Min Act: -0.0000

Data Index: 524507 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.1042. Min Act: -0.0000

Data Index: 341725 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1060918 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0719. Min Act: -0.0000

Data Index: 745060 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0648. Min Act: -0.0000

Data Index: 233995 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.7348. Min Range: -1.7348

Max Act: 0.9968. Min Act: -0.0000

Data Index: 384919 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0572. Min Act: -0.0000

Data Index: 679298 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0472. Min Act: -0.0000

Data Index: 105021 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0487. Min Act: -0.0000

Data Index: 380442 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.0567. Min Act: -0.0000

Data Index: 505520 (C4 (Web Text))

Max Activating Token Index: 571