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

Dataset: The Pile

Neuron 2000 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: 0.8285. Min Range: -0.8285

Max Act: 0.8285. Min Act: -0.0000

Data Index: 451534 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.8233. Min Act: -0.0000

Data Index: 428078 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7459. Min Act: -0.0000

Data Index: 166993 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7769. Min Act: -0.0000

Data Index: 649065 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1449891 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7361. Min Act: -0.0000

Data Index: 129022 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1791396 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1823932 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1832923 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6912. Min Act: -0.0000

Data Index: 155627 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1666744 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1360591 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1990069 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1337349 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1962453 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1768138 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1449515 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1018720 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6472. Min Act: -0.0000

Data Index: 365618 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1326661 (The Pile)

Max Activating Token Index: 219