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

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

Neuron 3328 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4442. Min Act: -0.0000

Data Index: 731412 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3438. Min Act: -0.0000

Data Index: 579575 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1197204 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2969. Min Act: -0.0000

Data Index: 518879 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2974. Min Act: -0.0000

Data Index: 77104 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1161508 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2996. Min Act: -0.0000

Data Index: 275843 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2973. Min Act: -0.0000

Data Index: 200307 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1224686 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1207985 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2733. Min Act: -0.0000

Data Index: 67849 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2657. Min Act: -0.0000

Data Index: 877971 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2742. Min Act: -0.0000

Data Index: 846548 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2551. Min Act: -0.0000

Data Index: 474042 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2557. Min Act: -0.0000

Data Index: 592646 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1362222 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2616. Min Act: -0.0000

Data Index: 561876 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2626. Min Act: -0.0000

Data Index: 457289 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2514. Min Act: -0.0000

Data Index: 201525 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1441029 (Python Code)

Max Activating Token Index: 864