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

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

Neuron 5778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.8397. Min Act: -0.0000

Data Index: 611335 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.6261. Min Act: -0.0000

Data Index: 1113996 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.7384. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1020752 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.2440. Min Act: -0.0000

Data Index: 21029 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.1706. Min Act: -0.0000

Data Index: 878605 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.0354. Min Act: -0.0000

Data Index: 1225128 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1268584 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.0014. Min Act: -0.0000

Data Index: 289620 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.1001. Min Act: -0.0000

Data Index: 1127002 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.1751. Min Act: -0.0000

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.1083. Min Act: -0.0000

Data Index: 1231422 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.0547. Min Act: -0.0000

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.8751. Min Act: -0.0000

Data Index: 372412 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.9225. Min Act: -0.0000

Data Index: 848925 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.8922. Min Act: -0.0000

Data Index: 839884 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.9468. Min Act: -0.0000

Data Index: 914480 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 2.8397. Min Range: -2.8397

Max Act: 2.0309. Min Act: -0.0000

Data Index: 300378 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.9214. Min Act: -0.0000

Data Index: 297855 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 2.8397. Min Range: -2.8397

Max Act: 1.8337. Min Act: -0.0000

Data Index: 263800 (C4 (Web Text))

Max Activating Token Index: 895