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

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

Neuron 5994 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.7238. Min Act: -0.0002

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.7114. Min Act: -0.0002

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.7263. Min Act: -0.0002

Data Index: 455604 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6765. Min Act: -0.0002

Data Index: 485409 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6547. Min Act: -0.0002

Data Index: 1253984 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6755. Min Act: -0.0002

Data Index: 601691 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6360. Min Act: -0.0002

Data Index: 1278221 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6231. Min Act: -0.0002

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5672. Min Act: -0.0002

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5813. Min Act: -0.0002

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5873. Min Act: -0.0002

Data Index: 166818 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5668. Min Act: -0.0002

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5322. Min Act: -0.0002

Data Index: 401888 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5179. Min Act: -0.0002

Data Index: 863655 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4826. Min Act: -0.0002

Data Index: 283496 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5244. Min Act: -0.0002

Data Index: 891578 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4133. Min Act: -0.0002

Data Index: 905965 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4389. Min Act: -0.0002

Data Index: 530563 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4429. Min Act: -0.0002

Data Index: 894364 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3848. Min Act: -0.0002

Data Index: 482457 (C4 (Web Text))

Max Activating Token Index: 880