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

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

Neuron 3319 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5586. Min Act: -0.0001

Data Index: 647054 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5524. Min Act: -0.0001

Data Index: 300721 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4563. Min Act: -0.0000

Data Index: 694746 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1047408 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4144. Min Act: -0.0001

Data Index: 545737 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4021. Min Act: -0.0001

Data Index: 243409 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1145280 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3935. Min Act: -0.0001

Data Index: 386096 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3543. Min Act: -0.0000

Data Index: 655380 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3605. Min Act: -0.0001

Data Index: 1081657 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3718. Min Act: -0.0001

Data Index: 57801 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1188126 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3421. Min Act: -0.0001

Data Index: 1248303 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3251. Min Act: -0.0001

Data Index: 107102 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3361. Min Act: -0.0000

Data Index: 497498 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3349. Min Act: -0.0000

Data Index: 773365 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1301554 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3177. Min Act: -0.0001

Data Index: 1326234 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3147. Min Act: -0.0000

Data Index: 221354 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3230. Min Act: -0.0001

Data Index: 444833 (C4 (Web Text))

Max Activating Token Index: 675