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

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

Neuron 757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1196995 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.7139. Min Act: -0.0001

Data Index: 969988 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6029. Min Act: -0.0001

Data Index: 1165618 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6197. Min Act: -0.0001

Data Index: 865612 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5962. Min Act: -0.0001

Data Index: 826140 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6810. Min Act: -0.0001

Data Index: 454591 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1092092 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6161. Min Act: -0.0001

Data Index: 762162 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1126527 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6619. Min Act: -0.0001

Data Index: 919986 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6371. Min Act: -0.0001

Data Index: 1116923 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1020060 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5713. Min Act: -0.0001

Data Index: 1270141 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5936. Min Act: -0.0001

Data Index: 1067978 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1009667 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6066. Min Act: -0.0001

Data Index: 938989 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1278697 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6179. Min Act: -0.0001

Data Index: 616873 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6229. Min Act: -0.0001

Data Index: 1332169 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6004. Min Act: -0.0001

Data Index: 75646 (C4 (Web Text))

Max Activating Token Index: 470