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

Dataset: The Pile

Neuron 3212 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: 1.1146. Min Range: -1.1146

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1874933 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.0143. Min Act: -0.0000

Data Index: 183886 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1876986 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7217. Min Act: -0.0000

Data Index: 439584 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8663. Min Act: -0.0000

Data Index: 798617 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1666599 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8079. Min Act: -0.0000

Data Index: 944231 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6769. Min Act: -0.0000

Data Index: 537713 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1175056 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7860. Min Act: -0.0000

Data Index: 76798 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8138. Min Act: -0.0000

Data Index: 57164 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7613. Min Act: -0.0000

Data Index: 779360 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6915. Min Act: -0.0000

Data Index: 971221 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1870515 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6725. Min Act: -0.0000

Data Index: 630232 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8612. Min Act: -0.0000

Data Index: 476879 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1320991 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6188. Min Act: -0.0000

Data Index: 640389 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1044678 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.6920. Min Act: -0.0000

Data Index: 99875 (The Pile)

Max Activating Token Index: 225