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

Dataset: The Pile

Neuron 833 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: 1.2411. Min Range: -1.2411

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1679524 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9817. Min Act: -0.0000

Data Index: 615886 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1421220 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8825. Min Act: -0.0000

Data Index: 996376 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1300808 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7132. Min Act: -0.0000

Data Index: 466509 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7567. Min Act: -0.0000

Data Index: 215413 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6822. Min Act: -0.0000

Data Index: 559582 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1780657 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8188. Min Act: -0.0000

Data Index: 854430 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7264. Min Act: -0.0000

Data Index: 956033 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1623803 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1171763 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1415612 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1410314 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1708529 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1094264 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1583275 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1216870 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1132375 (The Pile)

Max Activating Token Index: 154