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

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

Neuron 5390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7356. Min Act: -0.0000

Data Index: 150985 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.5653. Min Act: -0.0000

Data Index: 398048 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.5418. Min Act: -0.0000

Data Index: 179394 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.5305. Min Act: -0.0000

Data Index: 953400 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.5116. Min Act: -0.0000

Data Index: 750919 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4877. Min Act: -0.0000

Data Index: 34372 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1346651 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4565. Min Act: -0.0000

Data Index: 947848 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4333. Min Act: -0.0000

Data Index: 740242 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4511. Min Act: -0.0000

Data Index: 370094 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1211504 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1184872 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4263. Min Act: -0.0000

Data Index: 519725 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3880. Min Act: -0.0000

Data Index: 691509 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3802. Min Act: -0.0000

Data Index: 512951 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3919. Min Act: -0.0000

Data Index: 916609 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3660. Min Act: -0.0000

Data Index: 886412 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3619. Min Act: -0.0000

Data Index: 598092 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.4021. Min Act: -0.0000

Data Index: 832706 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.3675. Min Act: -0.0000

Data Index: 494546 (C4 (Web Text))

Max Activating Token Index: 255