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

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

Neuron 269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3734. Min Act: -0.0000

Data Index: 656995 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3186. Min Act: -0.0000

Data Index: 688008 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.6967. Min Act: -0.0000

Data Index: 855720 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.7712. Min Act: -0.0000

Data Index: 620228 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.6866. Min Act: -0.0000

Data Index: 802174 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.7995. Min Act: -0.0000

Data Index: 1107276 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.6196. Min Act: -0.0000

Data Index: 499560 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.6416. Min Act: -0.0000

Data Index: 1270045 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.3828. Min Act: -0.0000

Data Index: 940193 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.5179. Min Act: -0.0000

Data Index: 449678 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4857. Min Act: -0.0000

Data Index: 637036 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.6101. Min Act: -0.0000

Data Index: 55055 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4565. Min Act: -0.0000

Data Index: 4790 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4440. Min Act: -0.0000

Data Index: 751044 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4003. Min Act: -0.0000

Data Index: 1095309 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.2842. Min Act: -0.0000

Data Index: 68536 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4978. Min Act: -0.0000

Data Index: 907875 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.2375. Min Act: -0.0000

Data Index: 1198039 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.4625. Min Act: -0.0000

Data Index: 1012358 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 3.3734. Min Range: -3.3734

Max Act: 2.0940. Min Act: -0.0000

Data Index: 1016332 (C4 (Web Text))

Max Activating Token Index: 280