Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 114 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5736. Min Act: -0.0003

Data Index: 1114149 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5175. Min Act: -0.0003

Data Index: 162651 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4660. Min Act: -0.0003

Data Index: 1194259 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4636. Min Act: -0.0003

Data Index: 1122870 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4449. Min Act: -0.0003

Data Index: 1027863 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4405. Min Act: -0.0003

Data Index: 1299498 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4256. Min Act: -0.0003

Data Index: 563914 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4332. Min Act: -0.0003

Data Index: 522341 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4438. Min Act: -0.0003

Data Index: 1299697 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4310. Min Act: -0.0003

Data Index: 260900 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4406. Min Act: -0.0003

Data Index: 266244 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4247. Min Act: -0.0003

Data Index: 668377 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4257. Min Act: -0.0003

Data Index: 784459 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4232. Min Act: -0.0003

Data Index: 216352 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4176. Min Act: -0.0003

Data Index: 442526 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4186. Min Act: -0.0003

Data Index: 691909 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4048. Min Act: -0.0003

Data Index: 85931 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4162. Min Act: -0.0003

Data Index: 422392 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.3952. Min Act: -0.0003

Data Index: 732340 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4223. Min Act: -0.0003

Data Index: 198520 (C4 (Web Text))

Max Activating Token Index: 852