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

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

Neuron 3718 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: 0.2221. Min Range: -0.2221

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1283547 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2135. Min Act: -0.0001

Data Index: 337008 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1811. Min Act: -0.0002

Data Index: 509423 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1831. Min Act: -0.0002

Data Index: 557698 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1865. Min Act: -0.0001

Data Index: 788347 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1844. Min Act: -0.0001

Data Index: 669776 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1685. Min Act: -0.0001

Data Index: 256403 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1590. Min Act: -0.0001

Data Index: 175620 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1606. Min Act: -0.0002

Data Index: 800052 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1661. Min Act: -0.0002

Data Index: 1293828 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1656. Min Act: -0.0002

Data Index: 314120 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1584. Min Act: -0.0001

Data Index: 904260 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1600. Min Act: -0.0001

Data Index: 913581 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1541. Min Act: -0.0002

Data Index: 917258 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1521. Min Act: -0.0001

Data Index: 350497 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1576. Min Act: -0.0001

Data Index: 703551 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1247417 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1334962 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1441. Min Act: -0.0001

Data Index: 865806 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1488. Min Act: -0.0002

Data Index: 170157 (C4 (Web Text))

Max Activating Token Index: 10