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

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

Neuron 65 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: 0.5521. Min Range: -0.5521

Max Act: 0.5521. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1194886 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.4186. Min Act: -0.0001

Data Index: 109814 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.4087. Min Act: -0.0001

Data Index: 1105929 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3673. Min Act: -0.0000

Data Index: 902324 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3629. Min Act: -0.0000

Data Index: 981460 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3838. Min Act: -0.0001

Data Index: 614747 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3571. Min Act: -0.0001

Data Index: 982748 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3570. Min Act: -0.0000

Data Index: 982936 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3499. Min Act: -0.0000

Data Index: 800917 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3467. Min Act: -0.0000

Data Index: 4279 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1293431 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3352. Min Act: -0.0000

Data Index: 394280 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3529. Min Act: -0.0000

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3301. Min Act: -0.0001

Data Index: 896480 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3250. Min Act: -0.0000

Data Index: 934303 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1270221 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3131. Min Act: -0.0000

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1047901 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.5521. Min Range: -0.5521

Max Act: 0.3054. Min Act: -0.0000

Data Index: 54582 (C4 (Web Text))

Max Activating Token Index: 280