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

Dataset: The Pile

Neuron 2973 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: 1.9406. Min Range: -1.9406

Max Act: 1.8063. Min Act: -0.0000

Data Index: 1565646 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.7959. Min Act: -0.0000

Data Index: 739369 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.9406. Min Act: 0.0000

Data Index: 1852285 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1288730 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.5470. Min Act: -0.0000

Data Index: 750350 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4434. Min Act: 0.0000

Data Index: 1601669 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.6100. Min Act: -0.0000

Data Index: 54079 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4141. Min Act: -0.0000

Data Index: 654689 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1302756 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4028. Min Act: -0.0000

Data Index: 1745649 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.5522. Min Act: -0.0000

Data Index: 112542 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4870. Min Act: -0.0000

Data Index: 206901 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1706953 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4785. Min Act: 0.0000

Data Index: 821288 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.5112. Min Act: -0.0000

Data Index: 239114 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.5372. Min Act: -0.0000

Data Index: 1108408 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4872. Min Act: -0.0000

Data Index: 500170 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.3182. Min Act: -0.0000

Data Index: 248680 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1767328 (The Pile)

Max Activating Token Index: 202

Text #19

Max Range: 1.9406. Min Range: -1.9406

Max Act: 1.4009. Min Act: 0.0000

Data Index: 187597 (The Pile)

Max Activating Token Index: 401