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

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

Neuron 5630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.9012. Min Act: -0.0002

Data Index: 511918 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.8899. Min Act: -0.0002

Data Index: 624107 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.9142. Min Act: -0.0002

Data Index: 613295 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.9120. Min Act: -0.0002

Data Index: 966556 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.8160. Min Act: -0.0002

Data Index: 385615 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.8126. Min Act: -0.0002

Data Index: 880236 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7795. Min Act: -0.0002

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.8357. Min Act: -0.0002

Data Index: 1335840 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7788. Min Act: -0.0002

Data Index: 456428 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7423. Min Act: -0.0002

Data Index: 963029 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7122. Min Act: -0.0002

Data Index: 896831 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7371. Min Act: -0.0002

Data Index: 708484 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6733. Min Act: -0.0002

Data Index: 542632 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7072. Min Act: -0.0002

Data Index: 204209 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6624. Min Act: -0.0002

Data Index: 975377 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7042. Min Act: -0.0002

Data Index: 486276 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6716. Min Act: -0.0002

Data Index: 539407 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6730. Min Act: -0.0002

Data Index: 696420 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6749. Min Act: -0.0002

Data Index: 1298758 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6562. Min Act: -0.0002

Data Index: 801966 (C4 (Web Text))

Max Activating Token Index: 498