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

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

Neuron 1027 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: 0.6659. Min Range: -0.6659

Max Act: 0.6659. Min Act: -0.0001

Data Index: 1054605 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1025299 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5082. Min Act: -0.0001

Data Index: 493445 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5010. Min Act: -0.0001

Data Index: 146332 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4227. Min Act: -0.0000

Data Index: 424357 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1166512 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4093. Min Act: -0.0000

Data Index: 961524 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3465. Min Act: -0.0000

Data Index: 156414 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1126303 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3521. Min Act: -0.0000

Data Index: 13945 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1080983 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3463. Min Act: -0.0000

Data Index: 462610 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3534. Min Act: -0.0001

Data Index: 764590 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1197749 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3531. Min Act: -0.0000

Data Index: 408913 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1014286 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1317044 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3368. Min Act: -0.0000

Data Index: 174113 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3168. Min Act: -0.0001

Data Index: 845887 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.3237. Min Act: -0.0000

Data Index: 974052 (C4 (Web Text))

Max Activating Token Index: 732