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

Dataset: The Pile

Neuron 2760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5985. Min Range: -3.5985

Max Act: 3.5985. Min Act: -0.0000

Data Index: 900233 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 3.5985. Min Range: -3.5985

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1556278 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.9913. Min Act: -0.0000

Data Index: 1795923 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.9496. Min Act: -0.0000

Data Index: 311646 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.9496. Min Act: -0.0000

Data Index: 147948 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.9910. Min Act: -0.0000

Data Index: 332401 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.6813. Min Act: -0.0000

Data Index: 1011286 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.9659. Min Act: -0.0000

Data Index: 322005 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.6025. Min Act: -0.0000

Data Index: 1899814 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.5677. Min Act: -0.0000

Data Index: 476923 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.1990. Min Act: -0.0000

Data Index: 694076 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.3507. Min Act: -0.0000

Data Index: 1245192 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.4180. Min Act: -0.0000

Data Index: 129622 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.4727. Min Act: -0.0000

Data Index: 348158 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.1966. Min Act: -0.0000

Data Index: 491855 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.5260. Min Act: -0.0000

Data Index: 1883878 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.1161. Min Act: -0.0000

Data Index: 1980921 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.3169. Min Act: -0.0000

Data Index: 1827486 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.1696. Min Act: -0.0000

Data Index: 353658 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 3.5985. Min Range: -3.5985

Max Act: 2.2788. Min Act: -0.0000

Data Index: 700119 (The Pile)

Max Activating Token Index: 905