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

Dataset: The Pile

Neuron 332 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: 0.4384. Min Range: -0.4384

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1760789 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3887. Min Act: -0.0000

Data Index: 116029 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3347. Min Act: 0.0000

Data Index: 216065 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3026. Min Act: -0.0000

Data Index: 515404 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1197016 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1198508 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1226516 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2970. Min Act: -0.0000

Data Index: 167256 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2752. Min Act: -0.0000

Data Index: 102778 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2806. Min Act: -0.0000

Data Index: 65768 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2794. Min Act: -0.0000

Data Index: 866108 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2558. Min Act: -0.0000

Data Index: 286638 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2563. Min Act: -0.0000

Data Index: 999229 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2469. Min Act: 0.0000

Data Index: 139058 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2936. Min Act: -0.0000

Data Index: 964321 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1799612 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2521. Min Act: 0.0001

Data Index: 297518 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1603169 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1414884 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2554. Min Act: -0.0000

Data Index: 598597 (The Pile)

Max Activating Token Index: 866