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

Dataset: The Pile

Neuron 4050 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: 3.8912. Min Range: -3.8912

Max Act: 3.7253. Min Act: -0.0000

Data Index: 296176 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.8912. Min Act: -0.0000

Data Index: 355885 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.8758. Min Act: -0.0000

Data Index: 222986 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.7872. Min Act: -0.0000

Data Index: 1326753 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.6684. Min Act: -0.0000

Data Index: 499990 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.1957. Min Act: -0.0000

Data Index: 184186 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.3826. Min Act: -0.0000

Data Index: 310660 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.1570. Min Act: -0.0000

Data Index: 114329 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.5878. Min Act: -0.0000

Data Index: 913417 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.4630. Min Act: -0.0000

Data Index: 400835 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.5247. Min Act: -0.0000

Data Index: 1180447 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.2093. Min Act: -0.0000

Data Index: 303692 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.4850. Min Act: -0.0000

Data Index: 381719 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.0974. Min Act: -0.0000

Data Index: 684001 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.0399. Min Act: -0.0000

Data Index: 1279978 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.1981. Min Act: -0.0000

Data Index: 1678418 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.3637. Min Act: -0.0000

Data Index: 714852 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.2438. Min Act: -0.0000

Data Index: 810713 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.4023. Min Act: -0.0000

Data Index: 1155680 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 3.8912. Min Range: -3.8912

Max Act: 3.4112. Min Act: -0.0000

Data Index: 1193676 (The Pile)

Max Activating Token Index: 52