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

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

Neuron 138 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: 0.4375. Min Range: -0.4375

Max Act: 0.4375. Min Act: -0.0000

Data Index: 390980 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1167949 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1231579 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1019841 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1096073 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3901. Min Act: -0.0000

Data Index: 832543 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3879. Min Act: -0.0000

Data Index: 452111 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3794. Min Act: -0.0000

Data Index: 850161 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3475. Min Act: -0.0000

Data Index: 339657 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3530. Min Act: -0.0000

Data Index: 988130 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3521. Min Act: -0.0001

Data Index: 502781 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1199717 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3470. Min Act: -0.0000

Data Index: 951010 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3506. Min Act: -0.0000

Data Index: 260029 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3062. Min Act: -0.0000

Data Index: 861608 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1077098 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3465. Min Act: -0.0000

Data Index: 390453 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3669. Min Act: -0.0000

Data Index: 419165 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3415. Min Act: -0.0000

Data Index: 167359 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.4375. Min Range: -0.4375

Max Act: 0.3344. Min Act: -0.0000

Data Index: 636071 (C4 (Web Text))

Max Activating Token Index: 919