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

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

Neuron 3149 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: 0.6189. Min Range: -0.6189

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1656919 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5366. Min Act: -0.0001

Data Index: 81999 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1421588 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.4418. Min Act: -0.0000

Data Index: 559987 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3821. Min Act: -0.0000

Data Index: 482424 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1374533 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1234737 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1635281 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3809. Min Act: -0.0000

Data Index: 633781 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1438643 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1137152 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1640885 (Python Code)

Max Activating Token Index: 388

Text #12

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3486. Min Act: -0.0000

Data Index: 12156 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3490. Min Act: -0.0000

Data Index: 918042 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3050. Min Act: -0.0000

Data Index: 423725 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1594828 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3313. Min Act: -0.0000

Data Index: 961027 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1524175 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3198. Min Act: -0.0000

Data Index: 78643 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1515601 (Python Code)

Max Activating Token Index: 809