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

Dataset: The Pile

Neuron 2418 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: 0.6438. Min Range: -0.6438

Max Act: 0.6438. Min Act: -0.0000

Data Index: 237477 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5764. Min Act: 0.0000

Data Index: 1987568 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5959. Min Act: 0.0000

Data Index: 326767 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5298. Min Act: -0.0000

Data Index: 179644 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4883. Min Act: -0.0000

Data Index: 364433 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5577. Min Act: 0.0000

Data Index: 966142 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1335933 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1299331 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4465. Min Act: -0.0000

Data Index: 175912 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1965695 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4536. Min Act: -0.0000

Data Index: 245402 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4250. Min Act: 0.0000

Data Index: 647589 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1255818 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4226. Min Act: 0.0000

Data Index: 1481820 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4154. Min Act: -0.0000

Data Index: 74224 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4094. Min Act: -0.0000

Data Index: 368934 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.4194. Min Act: -0.0000

Data Index: 307755 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.3775. Min Act: 0.0000

Data Index: 1418870 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.3781. Min Act: -0.0000

Data Index: 124936 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.3821. Min Act: 0.0000

Data Index: 806583 (The Pile)

Max Activating Token Index: 925