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

Dataset: The Pile

Neuron 3655 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: 0.7675. Min Range: -0.7675

Max Act: 0.7505. Min Act: -0.0000

Data Index: 282406 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7675. Min Act: -0.0000

Data Index: 516467 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1649673 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1955684 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1051675 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7526. Min Act: -0.0000

Data Index: 181155 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1509704 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7350. Min Act: -0.0000

Data Index: 711783 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1907881 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7333. Min Act: -0.0000

Data Index: 529582 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1762443 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1163406 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1410213 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1877361 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1616835 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1851141 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6708. Min Act: -0.0000

Data Index: 99231 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1792015 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6938. Min Act: -0.0000

Data Index: 71894 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1542139 (The Pile)

Max Activating Token Index: 519