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

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

Neuron 3317 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: 2.6704. Min Range: -2.6704

Max Act: 2.6704. Min Act: -0.0000

Data Index: 913008 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.5957. Min Act: -0.0000

Data Index: 1052481 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.3933. Min Act: -0.0000

Data Index: 1254826 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.2680. Min Act: -0.0000

Data Index: 943801 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.2259. Min Act: -0.0000

Data Index: 1191619 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.1427. Min Act: -0.0000

Data Index: 1625228 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8739. Min Act: -0.0000

Data Index: 250879 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8352. Min Act: 0.0001

Data Index: 588340 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7714. Min Act: -0.0000

Data Index: 391438 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7789. Min Act: 0.0000

Data Index: 1400821 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7821. Min Act: -0.0000

Data Index: 953943 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7357. Min Act: -0.0000

Data Index: 946557 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6315. Min Act: -0.0000

Data Index: 1504639 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6518. Min Act: -0.0000

Data Index: 860865 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6276. Min Act: -0.0000

Data Index: 865788 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1367723 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.5645. Min Act: -0.0000

Data Index: 879225 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.5453. Min Act: -0.0000

Data Index: 697251 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.5395. Min Act: -0.0000

Data Index: 514307 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6239. Min Act: -0.0000

Data Index: 955279 (C4 (Web Text))

Max Activating Token Index: 143