Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1454. Min Range: -2.1454

Max Act: 2.1454. Min Act: -0.0000

Data Index: 965427 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.5408. Min Act: -0.0000

Data Index: 723293 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.6669. Min Act: -0.0000

Data Index: 568123 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.5676. Min Act: -0.0000

Data Index: 559800 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.6557. Min Act: -0.0000

Data Index: 108654 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3969. Min Act: -0.0000

Data Index: 218403 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1471597 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1525753 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1593501 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3265. Min Act: -0.0000

Data Index: 442943 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3262. Min Act: -0.0000

Data Index: 4006 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.4650. Min Act: -0.0000

Data Index: 81169 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1509485 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3346. Min Act: -0.0000

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1160409 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.2426. Min Act: -0.0000

Data Index: 347550 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1271431 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.2191. Min Act: -0.0000

Data Index: 224458 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.2742. Min Act: -0.0000

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.1454. Min Range: -2.1454

Max Act: 1.2632. Min Act: -0.0000

Data Index: 20606 (C4 (Web Text))

Max Activating Token Index: 646