Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.8765. Min Act: -0.0001

Data Index: 899261 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.9305. Min Act: -0.0001

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.4206. Min Act: -0.0001

Data Index: 450521 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.3543. Min Act: -0.0001

Data Index: 134265 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.3207. Min Act: -0.0001

Data Index: 608101 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.8590. Min Act: -0.0001

Data Index: 686662 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.6419. Min Act: -0.0001

Data Index: 288694 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.9321. Min Act: -0.0001

Data Index: 1137503 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 3.9305. Min Range: -3.9305

Max Act: 3.0801. Min Act: -0.0001

Data Index: 1097316 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.9160. Min Act: -0.0001

Data Index: 690913 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.7627. Min Act: -0.0001

Data Index: 25446 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.8709. Min Act: -0.0001

Data Index: 854569 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.5834. Min Act: -0.0001

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.6705. Min Act: -0.0001

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.7816. Min Act: -0.0001

Data Index: 1080641 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.5677. Min Act: -0.0001

Data Index: 179062 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.4530. Min Act: -0.0001

Data Index: 180518 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.6246. Min Act: -0.0001

Data Index: 1140166 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.4861. Min Act: -0.0001

Data Index: 23516 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 3.9305. Min Range: -3.9305

Max Act: 2.4660. Min Act: -0.0001

Data Index: 200733 (C4 (Web Text))

Max Activating Token Index: 901