Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2148 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2689. Min Range: -2.2689

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1269685 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.9909. Min Act: -0.0000

Data Index: 654803 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.9364. Min Act: -0.0000

Data Index: 1033927 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.8701. Min Act: -0.0000

Data Index: 466703 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.9235. Min Act: -0.0000

Data Index: 408129 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1199994 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.7734. Min Act: -0.0000

Data Index: 875737 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.7552. Min Act: -0.0000

Data Index: 927354 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1056821 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.7438. Min Act: -0.0000

Data Index: 419153 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6992. Min Act: -0.0000

Data Index: 1210762 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6205. Min Act: -0.0000

Data Index: 450957 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1062934 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6381. Min Act: -0.0000

Data Index: 909229 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1287530 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6483. Min Act: -0.0000

Data Index: 626485 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6942. Min Act: -0.0000

Data Index: 321001 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.6520. Min Act: -0.0000

Data Index: 286707 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.5883. Min Act: -0.0000

Data Index: 480704 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.2689. Min Range: -2.2689

Max Act: 1.5870. Min Act: -0.0000

Data Index: 628696 (C4 (Web Text))

Max Activating Token Index: 768