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

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

Neuron 2893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1144. Min Act: -0.0002

Data Index: 109609 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0002

Data Index: 465757 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1900 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1226959 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1045. Min Act: -0.0001

Data Index: 745536 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1036. Min Act: -0.0001

Data Index: 741274 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1029. Min Act: -0.0001

Data Index: 964823 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1003. Min Act: -0.0001

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0937. Min Act: -0.0002

Data Index: 30918 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1555601 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0981. Min Act: -0.0001

Data Index: 269856 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1019715 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1304629 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0947. Min Act: -0.0002

Data Index: 340773 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0963. Min Act: -0.0001

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1032909 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0959. Min Act: -0.0001

Data Index: 718470 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0929. Min Act: -0.0002

Data Index: 265496 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0925. Min Act: -0.0001

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0979. Min Act: -0.0001

Data Index: 234045 (C4 (Web Text))

Max Activating Token Index: 691