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

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

Neuron 5896 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.5279. Min Act: -0.0000

Data Index: 679323 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1350341 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3742. Min Act: -0.0000

Data Index: 596070 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3285. Min Act: -0.0000

Data Index: 410863 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3108. Min Act: -0.0000

Data Index: 974652 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3007. Min Act: 0.0001

Data Index: 328472 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3118. Min Act: 0.0000

Data Index: 784042 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2854. Min Act: -0.0000

Data Index: 311480 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1315004 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1007188 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2931. Min Act: 0.0000

Data Index: 209766 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2712. Min Act: -0.0000

Data Index: 806127 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2881. Min Act: -0.0000

Data Index: 661704 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2755. Min Act: 0.0000

Data Index: 578153 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2755. Min Act: -0.0000

Data Index: 150204 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2832. Min Act: 0.0000

Data Index: 87930 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2666. Min Act: 0.0001

Data Index: 391073 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2798. Min Act: -0.0000

Data Index: 378469 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2683. Min Act: 0.0000

Data Index: 615160 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.2664. Min Act: -0.0000

Data Index: 991455 (C4 (Web Text))

Max Activating Token Index: 834