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

Dataset: The Pile

Neuron 1481 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1475176 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1233376 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1929001 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1349510 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3121. Min Act: -0.0000

Data Index: 980040 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3097. Min Act: -0.0000

Data Index: 607372 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1630389 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1703119 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1283433 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2863. Min Act: -0.0000

Data Index: 632893 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2699. Min Act: -0.0000

Data Index: 633314 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2451. Min Act: -0.0000

Data Index: 272735 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2511. Min Act: -0.0000

Data Index: 293467 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1686925 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2735. Min Act: -0.0000

Data Index: 739455 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2759. Min Act: -0.0000

Data Index: 10287 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1640028 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2354. Min Act: -0.0000

Data Index: 889171 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2625. Min Act: -0.0000

Data Index: 95617 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1731940 (The Pile)

Max Activating Token Index: 292