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

Dataset: The Pile

Neuron 3823 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: 0.5270. Min Range: -0.5270

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1809130 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1618929 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1621287 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4993. Min Act: -0.0000

Data Index: 971038 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1328953 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1419258 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1452189 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4589. Min Act: -0.0000

Data Index: 338325 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1354027 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4607. Min Act: -0.0000

Data Index: 897838 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4650. Min Act: -0.0000

Data Index: 551017 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1414069 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1211297 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4141. Min Act: -0.0000

Data Index: 967025 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1935087 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1636589 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1987763 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4363. Min Act: -0.0000

Data Index: 25988 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1019609 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1331146 (The Pile)

Max Activating Token Index: 767