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

Dataset: The Pile

Neuron 1502 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: 4.4443. Min Range: -4.4443

Max Act: 4.1872. Min Act: -0.0000

Data Index: 1398101 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.4443. Min Act: -0.0000

Data Index: 1924230 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.2780. Min Act: -0.0000

Data Index: 1699667 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.0133. Min Act: -0.0000

Data Index: 113260 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.9549. Min Act: -0.0000

Data Index: 126417 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.0903. Min Act: -0.0000

Data Index: 1661196 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.5996. Min Act: -0.0000

Data Index: 388907 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.0790. Min Act: -0.0000

Data Index: 1133797 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.2430. Min Act: -0.0000

Data Index: 514365 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.0477. Min Act: -0.0000

Data Index: 1929378 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 4.4443. Min Range: -4.4443

Max Act: 4.2160. Min Act: -0.0000

Data Index: 923674 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.8755. Min Act: -0.0000

Data Index: 1914303 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.9759. Min Act: -0.0000

Data Index: 1555605 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.9584. Min Act: -0.0000

Data Index: 648430 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.9434. Min Act: -0.0000

Data Index: 1631036 (The Pile)

Max Activating Token Index: 614

Text #15

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.9030. Min Act: -0.0000

Data Index: 753587 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.8758. Min Act: -0.0000

Data Index: 1230145 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.7035. Min Act: -0.0000

Data Index: 1259933 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.8720. Min Act: -0.0000

Data Index: 363770 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 4.4443. Min Range: -4.4443

Max Act: 3.8075. Min Act: -0.0000

Data Index: 372235 (The Pile)

Max Activating Token Index: 448