Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2951. Min Range: -2.2951

Max Act: 2.2128. Min Act: -0.0000

Data Index: 44478 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.2951. Min Range: -2.2951

Max Act: 2.1525. Min Act: -0.0000

Data Index: 1017780 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 2.2951. Min Range: -2.2951

Max Act: 2.2256. Min Act: -0.0000

Data Index: 389324 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.2951. Min Range: -2.2951

Max Act: 2.2951. Min Act: -0.0000

Data Index: 459730 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 2.2951. Min Range: -2.2951

Max Act: 2.1258. Min Act: -0.0000

Data Index: 11990 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7442. Min Act: -0.0000

Data Index: 1228706 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.9293. Min Act: -0.0000

Data Index: 958958 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.9085. Min Act: -0.0000

Data Index: 78025 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1356641 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.9590. Min Act: -0.0000

Data Index: 191747 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.8631. Min Act: -0.0000

Data Index: 273796 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1175758 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7896. Min Act: -0.0000

Data Index: 1034210 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7136. Min Act: -0.0000

Data Index: 687786 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.6241. Min Act: -0.0000

Data Index: 178443 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7139. Min Act: -0.0000

Data Index: 847059 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.6945. Min Act: -0.0000

Data Index: 551155 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.7636. Min Act: -0.0000

Data Index: 1168798 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.6665. Min Act: -0.0000

Data Index: 884204 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.2951. Min Range: -2.2951

Max Act: 1.6557. Min Act: -0.0000

Data Index: 624474 (C4 (Web Text))

Max Activating Token Index: 800