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

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

Neuron 1705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4304. Min Range: -3.4304

Max Act: 3.4304. Min Act: -0.0001

Data Index: 823896 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.6498. Min Act: -0.0001

Data Index: 229189 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.5283. Min Act: -0.0001

Data Index: 340001 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.2794. Min Act: -0.0001

Data Index: 242671 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.8483. Min Act: -0.0001

Data Index: 750341 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.2738. Min Act: -0.0001

Data Index: 1172122 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.2244. Min Act: -0.0001

Data Index: 929869 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.9118. Min Act: -0.0001

Data Index: 345567 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.2048. Min Act: -0.0001

Data Index: 837337 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.2015. Min Act: -0.0001

Data Index: 1156648 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.0637. Min Act: -0.0001

Data Index: 980997 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.8269. Min Act: -0.0001

Data Index: 61788 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.1120. Min Act: -0.0001

Data Index: 180426 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.9159. Min Act: -0.0001

Data Index: 694078 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.0094. Min Act: -0.0001

Data Index: 394749 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.8168. Min Act: -0.0001

Data Index: 551742 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.0456. Min Act: -0.0001

Data Index: 368375 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 3.4304. Min Range: -3.4304

Max Act: 1.8536. Min Act: -0.0001

Data Index: 776474 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.1745. Min Act: -0.0001

Data Index: 1243409 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.4304. Min Range: -3.4304

Max Act: 2.0354. Min Act: -0.0001

Data Index: 115635 (C4 (Web Text))

Max Activating Token Index: 548