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

Dataset: The Pile

Neuron 1837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1335583 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1559160 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2936. Min Act: -0.0000

Data Index: 535444 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1262570 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3054. Min Act: -0.0000

Data Index: 133259 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1877037 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1691775 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2879. Min Act: -0.0000

Data Index: 934175 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2866. Min Act: -0.0000

Data Index: 628436 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1064294 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2448. Min Act: -0.0000

Data Index: 80683 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2793. Min Act: -0.0000

Data Index: 496410 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2752. Min Act: -0.0000

Data Index: 63797 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2706. Min Act: -0.0000

Data Index: 878835 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2607. Min Act: -0.0000

Data Index: 72147 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2833. Min Act: -0.0000

Data Index: 840822 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2646. Min Act: -0.0000

Data Index: 233642 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2636. Min Act: -0.0000

Data Index: 402589 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2587. Min Act: -0.0000

Data Index: 694122 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2751. Min Act: -0.0000

Data Index: 863179 (The Pile)

Max Activating Token Index: 793