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

Dataset: The Pile

Neuron 1491 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: 0.7450. Min Range: -0.7450

Max Act: 0.7450. Min Act: -0.0000

Data Index: 516688 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6530. Min Act: -0.0000

Data Index: 97799 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6686. Min Act: -0.0000

Data Index: 708676 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1140710 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1250351 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1259940 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1224499 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6150. Min Act: -0.0000

Data Index: 606977 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5752. Min Act: -0.0000

Data Index: 354020 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1606543 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1105570 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1751649 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1004229 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1224464 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5744. Min Act: -0.0000

Data Index: 985104 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1525719 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1931498 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5717. Min Act: -0.0000

Data Index: 434570 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1535644 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6160. Min Act: -0.0000

Data Index: 990143 (The Pile)

Max Activating Token Index: 749