Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1348735 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1245826 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4805. Min Act: -0.0000

Data Index: 83347 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4708. Min Act: -0.0000

Data Index: 538889 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4691. Min Act: -0.0001

Data Index: 1293486 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4859. Min Act: -0.0001

Data Index: 1065874 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4494. Min Act: -0.0000

Data Index: 518349 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4450. Min Act: -0.0000

Data Index: 245991 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4564. Min Act: -0.0000

Data Index: 966230 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4403. Min Act: -0.0001

Data Index: 958191 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4370. Min Act: -0.0000

Data Index: 598029 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4825. Min Act: -0.0001

Data Index: 294517 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4354. Min Act: -0.0000

Data Index: 999968 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4429. Min Act: -0.0000

Data Index: 10868 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4302. Min Act: -0.0000

Data Index: 492472 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4425. Min Act: -0.0000

Data Index: 219968 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1337595 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4533. Min Act: -0.0001

Data Index: 180604 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1077865 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4362. Min Act: -0.0000

Data Index: 845573 (C4 (Web Text))

Max Activating Token Index: 787