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

Dataset: The Pile

Neuron 1732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1577620 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1828731 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0000

Data Index: 814806 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6383. Min Act: -0.0000

Data Index: 750211 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1221482 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5731. Min Act: -0.0000

Data Index: 119222 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6167. Min Act: -0.0000

Data Index: 973214 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1173634 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1514741 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5010. Min Act: -0.0000

Data Index: 420535 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5360. Min Act: -0.0000

Data Index: 676597 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1371987 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5254. Min Act: -0.0000

Data Index: 442652 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5198. Min Act: -0.0000

Data Index: 193949 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1298587 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4983. Min Act: -0.0000

Data Index: 905190 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4443. Min Act: -0.0000

Data Index: 566796 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4431. Min Act: -0.0000

Data Index: 51168 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4779. Min Act: -0.0000

Data Index: 870046 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1121113 (The Pile)

Max Activating Token Index: 552