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

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

Neuron 3386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3085. Min Range: -5.3085

Max Act: 5.3085. Min Act: -0.0000

Data Index: 200786 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.7067. Min Act: -0.0000

Data Index: 1137011 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.4812. Min Act: -0.0000

Data Index: 240175 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.3836. Min Act: -0.0000

Data Index: 592154 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.3519. Min Act: -0.0000

Data Index: 999416 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.5325. Min Act: -0.0000

Data Index: 1237648 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.5055. Min Act: -0.0000

Data Index: 515853 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.8560. Min Act: -0.0000

Data Index: 81726 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.4304. Min Act: -0.0000

Data Index: 431796 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.3555. Min Act: -0.0000

Data Index: 1087127 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.1307. Min Act: -0.0000

Data Index: 129655 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.1464. Min Act: -0.0000

Data Index: 454241 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 5.3085. Min Range: -5.3085

Max Act: 3.7950. Min Act: -0.0000

Data Index: 909662 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.2444. Min Act: -0.0000

Data Index: 905869 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.0581. Min Act: -0.0000

Data Index: 938960 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.2345. Min Act: -0.0000

Data Index: 778023 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.2169. Min Act: -0.0000

Data Index: 1306369 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.2095. Min Act: -0.0000

Data Index: 589991 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.0462. Min Act: -0.0000

Data Index: 686719 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 5.3085. Min Range: -5.3085

Max Act: 4.2103. Min Act: -0.0000

Data Index: 1324666 (C4 (Web Text))

Max Activating Token Index: 112