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

Dataset: The Pile

Neuron 4930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6769. Min Act: -0.0000

Data Index: 83108 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6688. Min Act: -0.0000

Data Index: 328286 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6964. Min Act: -0.0000

Data Index: 90624 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1368637 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1060421 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1195050 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1404257 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1269725 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4710. Min Act: -0.0000

Data Index: 545840 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1613523 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1234380 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1690663 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4491. Min Act: -0.0000

Data Index: 52091 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1632376 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4694. Min Act: -0.0000

Data Index: 887575 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1105952 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.3893. Min Act: -0.0000

Data Index: 362508 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1124214 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4543. Min Act: -0.0000

Data Index: 458971 (The Pile)

Max Activating Token Index: 342