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

Dataset: The Pile

Neuron 1428 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.8686. Min Act: -0.0000

Data Index: 1651303 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.9021. Min Act: -0.0000

Data Index: 384878 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.8126. Min Act: -0.0000

Data Index: 1769711 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.8514. Min Act: -0.0000

Data Index: 397036 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1070811 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.5701. Min Act: -0.0000

Data Index: 163517 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1063666 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.4537. Min Act: -0.0000

Data Index: 660092 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.6300. Min Act: -0.0000

Data Index: 1748553 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1541914 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3088. Min Act: -0.0000

Data Index: 663377 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1669596 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3478. Min Act: -0.0000

Data Index: 459096 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1724174 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1124542 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1205605 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1193067 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3063. Min Act: -0.0000

Data Index: 688299 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1427762 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 1.9021. Min Range: -1.9021

Max Act: 1.1409. Min Act: -0.0000

Data Index: 607261 (The Pile)

Max Activating Token Index: 644