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

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

Neuron 84 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4437. Min Range: -2.4437

Max Act: 2.4437. Min Act: -0.0000

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 2.4437. Min Range: -2.4437

Max Act: 2.1179. Min Act: -0.0000

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 2.4437. Min Range: -2.4437

Max Act: 2.0248. Min Act: -0.0000

Data Index: 830053 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.4437. Min Range: -2.4437

Max Act: 2.0201. Min Act: -0.0000

Data Index: 215658 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.9135. Min Act: -0.0000

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.8970. Min Act: -0.0000

Data Index: 773623 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.8053. Min Act: -0.0000

Data Index: 441660 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1161234 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1295924 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.5101. Min Act: -0.0000

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4247. Min Act: -0.0000

Data Index: 545141 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4322. Min Act: -0.0000

Data Index: 237713 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1019198 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4710. Min Act: -0.0000

Data Index: 493070 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4399. Min Act: -0.0000

Data Index: 972502 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.4180. Min Act: -0.0000

Data Index: 464488 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.3920. Min Act: -0.0000

Data Index: 941279 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1415944 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 2.4437. Min Range: -2.4437

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1307183 (C4 (Web Text))

Max Activating Token Index: 814