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

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

Neuron 3946 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: 1.7137. Min Range: -1.7137

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1034752 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.6999. Min Act: -0.0000

Data Index: 544231 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.7137. Min Act: -0.0000

Data Index: 861643 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4052. Min Act: -0.0000

Data Index: 1263689 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4423. Min Act: -0.0000

Data Index: 687298 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1272345 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4313. Min Act: -0.0000

Data Index: 183478 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1114463 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1378152 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.4300. Min Act: -0.0000

Data Index: 270105 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2672. Min Act: -0.0000

Data Index: 245878 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2822. Min Act: -0.0000

Data Index: 874446 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2975. Min Act: -0.0000

Data Index: 690672 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2276. Min Act: -0.0000

Data Index: 407404 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2151. Min Act: -0.0000

Data Index: 410086 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2872. Min Act: -0.0000

Data Index: 507414 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1222053 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2210. Min Act: -0.0000

Data Index: 881731 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.1871. Min Act: -0.0000

Data Index: 210789 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.7137. Min Range: -1.7137

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1348764 (C4 (Web Text))

Max Activating Token Index: 319