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

Dataset: The Pile

Neuron 3978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1302049 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7129. Min Act: -0.0000

Data Index: 355716 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7106. Min Act: -0.0000

Data Index: 99217 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7125. Min Act: -0.0000

Data Index: 818031 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5733. Min Act: -0.0000

Data Index: 555091 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1881715 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6710. Min Act: -0.0000

Data Index: 783108 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6343. Min Act: -0.0000

Data Index: 353113 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6306. Min Act: -0.0000

Data Index: 437424 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1244335 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6085. Min Act: -0.0000

Data Index: 525952 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1115331 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7253. Min Act: -0.0000

Data Index: 663866 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1059872 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4252. Min Act: -0.0000

Data Index: 795848 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 396436 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5165. Min Act: 0.0000

Data Index: 621596 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5580. Min Act: 0.0000

Data Index: 238710 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1934440 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4510. Min Act: -0.0001

Data Index: 109374 (The Pile)

Max Activating Token Index: 265