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

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

Neuron 3619 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: 4.7528. Min Range: -4.7528

Max Act: 4.7528. Min Act: -0.0000

Data Index: 71177 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 4.7528. Min Range: -4.7528

Max Act: 4.3061. Min Act: -0.0000

Data Index: 1156648 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 4.7528. Min Range: -4.7528

Max Act: 4.5180. Min Act: -0.0000

Data Index: 340532 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 4.7528. Min Range: -4.7528

Max Act: 4.0805. Min Act: -0.0000

Data Index: 710489 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.9901. Min Act: -0.0000

Data Index: 1161289 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.9617. Min Act: -0.0000

Data Index: 615446 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.5932. Min Act: -0.0000

Data Index: 286909 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.9061. Min Act: -0.0000

Data Index: 662955 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.7141. Min Act: -0.0000

Data Index: 1105092 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.6422. Min Act: -0.0000

Data Index: 1221156 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.4129. Min Act: -0.0000

Data Index: 150924 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.7644. Min Act: -0.0000

Data Index: 291693 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.8893. Min Act: -0.0000

Data Index: 535388 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.3065. Min Act: -0.0000

Data Index: 285388 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.5768. Min Act: -0.0000

Data Index: 1137493 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.5114. Min Act: -0.0000

Data Index: 948237 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.5341. Min Act: -0.0000

Data Index: 713887 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.3022. Min Act: -0.0000

Data Index: 1078414 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.4085. Min Act: -0.0000

Data Index: 1305769 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 4.7528. Min Range: -4.7528

Max Act: 3.4246. Min Act: -0.0000

Data Index: 1312445 (C4 (Web Text))

Max Activating Token Index: 31