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

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

Neuron 4741 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: 1.8661. Min Range: -1.8661

Max Act: 1.7587. Min Act: -0.0000

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.8661. Min Act: -0.0000

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5533. Min Act: -0.0000

Data Index: 514105 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5567. Min Act: -0.0000

Data Index: 107587 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4508. Min Act: -0.0000

Data Index: 167824 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5410. Min Act: -0.0000

Data Index: 1301804 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5311. Min Act: -0.0000

Data Index: 471231 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5030. Min Act: -0.0000

Data Index: 607347 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4902. Min Act: -0.0000

Data Index: 122222 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4705. Min Act: -0.0000

Data Index: 399562 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4530. Min Act: -0.0000

Data Index: 126775 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1285082 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4470. Min Act: -0.0000

Data Index: 236240 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.3399. Min Act: -0.0000

Data Index: 288958 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4156. Min Act: -0.0000

Data Index: 146744 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4149. Min Act: -0.0000

Data Index: 980434 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4192. Min Act: -0.0000

Data Index: 57703 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5087. Min Act: -0.0000

Data Index: 552311 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4022. Min Act: -0.0000

Data Index: 516702 (C4 (Web Text))

Max Activating Token Index: 255