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

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

Neuron 3346 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: 1.6775. Min Range: -1.6775

Max Act: 1.6775. Min Act: -0.0000

Data Index: 389356 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1472838 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.6170. Min Act: -0.0000

Data Index: 648768 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.5331. Min Act: -0.0000

Data Index: 787335 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1625669 (Python Code)

Max Activating Token Index: 534

Text #5

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.4788. Min Act: -0.0000

Data Index: 630350 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.5458. Min Act: -0.0000

Data Index: 486441 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1332097 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.3756. Min Act: -0.0000

Data Index: 626485 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1319262 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1554653 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1087709 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2572. Min Act: -0.0000

Data Index: 444192 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2826. Min Act: -0.0000

Data Index: 314141 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1064798 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2628. Min Act: -0.0000

Data Index: 583019 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2161. Min Act: -0.0000

Data Index: 336459 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1373991 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.1603. Min Act: -0.0000

Data Index: 814105 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.6775. Min Range: -1.6775

Max Act: 1.2598. Min Act: -0.0000

Data Index: 473993 (C4 (Web Text))

Max Activating Token Index: 353