Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 89 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.0381. Min Range: -2.0381

Max Act: 2.0381. Min Act: -0.0002

Data Index: 1020421 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.9510. Min Act: -0.0002

Data Index: 439133 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.8740. Min Act: -0.0002

Data Index: 1236046 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.9031. Min Act: -0.0002

Data Index: 1295243 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.8647. Min Act: -0.0002

Data Index: 854623 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.7976. Min Act: -0.0002

Data Index: 642329 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.8318. Min Act: -0.0002

Data Index: 359794 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.7515. Min Act: -0.0002

Data Index: 1273703 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.7133. Min Act: -0.0002

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6814. Min Act: -0.0002

Data Index: 707198 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6594. Min Act: -0.0002

Data Index: 30475 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6362. Min Act: -0.0002

Data Index: 271891 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6429. Min Act: -0.0002

Data Index: 469814 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6566. Min Act: -0.0002

Data Index: 641220 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6069. Min Act: -0.0002

Data Index: 646631 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6262. Min Act: -0.0002

Data Index: 128284 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.5773. Min Act: -0.0002

Data Index: 550499 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.6380. Min Act: -0.0002

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.5626. Min Act: -0.0002

Data Index: 441926 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 2.0381. Min Range: -2.0381

Max Act: 1.5516. Min Act: -0.0002

Data Index: 5171 (C4 (Web Text))

Max Activating Token Index: 688