Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2822 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2364. Min Act: -0.0001

Data Index: 545579 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2480. Min Act: -0.0001

Data Index: 550816 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2246. Min Act: -0.0001

Data Index: 627759 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1965. Min Act: -0.0001

Data Index: 317024 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2462. Min Act: -0.0001

Data Index: 958486 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2161. Min Act: -0.0001

Data Index: 123813 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2198. Min Act: -0.0001

Data Index: 355494 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2293. Min Act: -0.0001

Data Index: 517692 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2329. Min Act: -0.0001

Data Index: 261214 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2038. Min Act: -0.0001

Data Index: 185006 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2362. Min Act: -0.0001

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2048. Min Act: -0.0001

Data Index: 668564 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2181. Min Act: -0.0001

Data Index: 687992 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1832. Min Act: -0.0001

Data Index: 684734 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1300270 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1986. Min Act: -0.0001

Data Index: 218312 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2253. Min Act: -0.0001

Data Index: 396312 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2072. Min Act: -0.0001

Data Index: 870701 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2149. Min Act: -0.0001

Data Index: 103585 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2106. Min Act: -0.0001

Data Index: 128860 (C4 (Web Text))

Max Activating Token Index: 385