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

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

Neuron 1567 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1056317 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3261. Min Act: -0.0000

Data Index: 260789 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3432. Min Act: -0.0000

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2927. Min Act: -0.0000

Data Index: 72173 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1064137 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3022. Min Act: -0.0000

Data Index: 384829 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1482640 (Python Code)

Max Activating Token Index: 250

Text #7

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2852. Min Act: -0.0000

Data Index: 402618 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1225096 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2596. Min Act: -0.0000

Data Index: 229068 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2451. Min Act: -0.0000

Data Index: 396864 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2582. Min Act: -0.0000

Data Index: 535935 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2472. Min Act: -0.0000

Data Index: 663879 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1147193 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2533. Min Act: -0.0000

Data Index: 654873 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2433. Min Act: -0.0000

Data Index: 748157 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2412. Min Act: -0.0000

Data Index: 141633 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2632. Min Act: -0.0000

Data Index: 40663 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2456. Min Act: -0.0000

Data Index: 68071 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.2482. Min Act: -0.0000

Data Index: 782775 (C4 (Web Text))

Max Activating Token Index: 133