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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.4056. Min Act: -0.0000

Data Index: 448651 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1267487 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3543. Min Act: -0.0000

Data Index: 358991 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3810. Min Act: -0.0000

Data Index: 595532 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3884. Min Act: -0.0000

Data Index: 880565 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1095608 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3719. Min Act: -0.0000

Data Index: 320144 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3754. Min Act: -0.0000

Data Index: 422913 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3768. Min Act: -0.0000

Data Index: 546970 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1177392 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3542. Min Act: -0.0000

Data Index: 894945 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1181663 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3498. Min Act: -0.0000

Data Index: 813286 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3491. Min Act: -0.0000

Data Index: 965236 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3515. Min Act: -0.0000

Data Index: 402602 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3326. Min Act: -0.0000

Data Index: 979861 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3125. Min Act: -0.0000

Data Index: 614543 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3152. Min Act: -0.0000

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3366. Min Act: -0.0000

Data Index: 900269 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.4056. Min Range: -0.4056

Max Act: 0.3198. Min Act: -0.0000

Data Index: 7297 (C4 (Web Text))

Max Activating Token Index: 430