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

Dataset: The Pile

Neuron 3395 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: 1.2365. Min Range: -1.2365

Max Act: 1.2365. Min Act: -0.0000

Data Index: 800195 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0972. Min Act: -0.0000

Data Index: 616326 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0238. Min Act: -0.0000

Data Index: 663365 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0787. Min Act: -0.0000

Data Index: 383064 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1616915 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0287. Min Act: -0.0000

Data Index: 265286 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1985177 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1657664 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1695442 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1191124 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9604. Min Act: -0.0000

Data Index: 852706 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1074483 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1987223 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1283439 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1980626 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1884614 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1548058 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1867192 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.8982. Min Act: -0.0000

Data Index: 617276 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1852782 (The Pile)

Max Activating Token Index: 381