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

Dataset: The Pile

Neuron 1287 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: 1.0406. Min Range: -1.0406

Max Act: 1.0406. Min Act: -0.0000

Data Index: 276103 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.0406. Min Range: -1.0406

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1999232 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1768174 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.8291. Min Act: -0.0000

Data Index: 967213 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7667. Min Act: -0.0000

Data Index: 255314 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1356165 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7772. Min Act: -0.0000

Data Index: 666337 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6954. Min Act: -0.0000

Data Index: 492084 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6835. Min Act: -0.0000

Data Index: 147603 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7369. Min Act: -0.0000

Data Index: 934022 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1756857 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7349. Min Act: -0.0000

Data Index: 362073 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1129966 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1783881 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1877729 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6900. Min Act: -0.0000

Data Index: 761862 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1042662 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6478. Min Act: -0.0000

Data Index: 112108 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7267. Min Act: -0.0000

Data Index: 26128 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1202554 (The Pile)

Max Activating Token Index: 466