Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 224 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1139957 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.4158. Min Act: -0.0000

Data Index: 701498 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1498943 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3726. Min Act: -0.0000

Data Index: 643530 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3403. Min Act: -0.0000

Data Index: 160099 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3251. Min Act: -0.0000

Data Index: 292916 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3348. Min Act: -0.0000

Data Index: 891207 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1467681 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3146. Min Act: -0.0000

Data Index: 27815 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1420863 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1274184 (The Pile)

Max Activating Token Index: 328

Text #11

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3047. Min Act: -0.0000

Data Index: 530833 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2849. Min Act: -0.0000

Data Index: 994342 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2864. Min Act: -0.0000

Data Index: 763089 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1970345 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1821702 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2756. Min Act: -0.0000

Data Index: 591876 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3023. Min Act: -0.0000

Data Index: 367534 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1598055 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1105540 (The Pile)

Max Activating Token Index: 713