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

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

Neuron 1130 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2579. Min Act: -0.0001

Data Index: 705944 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2410. Min Act: -0.0001

Data Index: 949396 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2272. Min Act: -0.0001

Data Index: 253179 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2347. Min Act: -0.0001

Data Index: 781644 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1330341 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2210. Min Act: -0.0001

Data Index: 999269 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2251. Min Act: -0.0001

Data Index: 402322 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2201. Min Act: -0.0001

Data Index: 626682 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2240. Min Act: -0.0001

Data Index: 464920 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2221. Min Act: -0.0001

Data Index: 966398 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1071869 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1060296 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2136. Min Act: -0.0001

Data Index: 709716 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2251. Min Act: -0.0001

Data Index: 453797 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2107. Min Act: -0.0001

Data Index: 6980 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2264. Min Act: -0.0001

Data Index: 354031 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2103. Min Act: -0.0001

Data Index: 786085 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2099. Min Act: -0.0001

Data Index: 345637 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2165. Min Act: -0.0001

Data Index: 643672 (C4 (Web Text))

Max Activating Token Index: 452