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

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

Neuron 509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1499. Min Act: -0.0001

Data Index: 457817 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1118766 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1484. Min Act: -0.0001

Data Index: 98471 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1357. Min Act: -0.0001

Data Index: 984661 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1276. Min Act: -0.0001

Data Index: 661995 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1622198 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1109988 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1151. Min Act: -0.0001

Data Index: 507792 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1138. Min Act: -0.0001

Data Index: 993148 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1106. Min Act: -0.0001

Data Index: 923141 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1145. Min Act: -0.0001

Data Index: 170025 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1196. Min Act: -0.0001

Data Index: 640414 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1104. Min Act: -0.0001

Data Index: 134051 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1165. Min Act: -0.0001

Data Index: 366095 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1024. Min Act: -0.0001

Data Index: 340725 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0982. Min Act: -0.0001

Data Index: 835599 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1327510 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1240175 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1105422 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0988. Min Act: -0.0001

Data Index: 586803 (C4 (Web Text))

Max Activating Token Index: 244