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

Dataset: The Pile

Neuron 779 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0125. Min Range: -3.0125

Max Act: 3.0125. Min Act: -0.0000

Data Index: 455200 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.4832. Min Act: -0.0000

Data Index: 107180 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.4067. Min Act: -0.0000

Data Index: 1200620 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.2280. Min Act: -0.0000

Data Index: 1340309 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.2184. Min Act: -0.0000

Data Index: 370565 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.1240. Min Act: -0.0000

Data Index: 1034418 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.0600. Min Act: -0.0000

Data Index: 296726 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.1669. Min Act: -0.0000

Data Index: 395475 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.1616. Min Act: -0.0000

Data Index: 1002350 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.0483. Min Act: -0.0000

Data Index: 985857 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9953. Min Act: -0.0000

Data Index: 512467 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.8912. Min Act: -0.0000

Data Index: 939067 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1939371 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.8535. Min Act: 0.0000

Data Index: 1279492 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9396. Min Act: -0.0000

Data Index: 1774634 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9169. Min Act: -0.0000

Data Index: 1670272 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9098. Min Act: 0.0001

Data Index: 1097546 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.1327. Min Act: -0.0000

Data Index: 384071 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9118. Min Act: -0.0000

Data Index: 1493994 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.8813. Min Act: -0.0000

Data Index: 710958 (The Pile)

Max Activating Token Index: 36