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

Dataset: The Pile

Neuron 2878 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: 1.1213. Min Range: -1.1213

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1690401 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1259569 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1053740 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0066. Min Act: -0.0000

Data Index: 608757 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1370465 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0604. Min Act: -0.0000

Data Index: 545147 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0499. Min Act: -0.0000

Data Index: 441658 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9696. Min Act: -0.0000

Data Index: 824262 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8849. Min Act: -0.0000

Data Index: 89933 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8866. Min Act: -0.0000

Data Index: 927792 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8333. Min Act: -0.0000

Data Index: 732891 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1401435 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8320. Min Act: -0.0000

Data Index: 973695 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8524. Min Act: -0.0000

Data Index: 558909 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1528248 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1135374 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1735273 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8240. Min Act: -0.0000

Data Index: 276934 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1209051 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7603. Min Act: -0.0000

Data Index: 338803 (The Pile)

Max Activating Token Index: 1010