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

Dataset: The Pile

Neuron 3232 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: 1.2213. Min Range: -1.2213

Max Act: 1.1927. Min Act: -0.0000

Data Index: 943376 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.2213. Min Act: -0.0000

Data Index: 368215 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.1314. Min Act: -0.0000

Data Index: 77209 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.1897. Min Act: -0.0000

Data Index: 313843 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1952578 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1042176 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0007. Min Act: -0.0000

Data Index: 66545 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0699. Min Act: -0.0000

Data Index: 998903 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1212107 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9475. Min Act: -0.0000

Data Index: 774775 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1134834 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0166. Min Act: -0.0000

Data Index: 718647 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9315. Min Act: -0.0000

Data Index: 578115 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9297. Min Act: -0.0000

Data Index: 334627 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1154883 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9225. Min Act: -0.0000

Data Index: 960958 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8646. Min Act: -0.0000

Data Index: 710589 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1993972 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8822. Min Act: -0.0000

Data Index: 245544 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8498. Min Act: -0.0000

Data Index: 132500 (The Pile)

Max Activating Token Index: 383