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

Dataset: The Pile

Neuron 96 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 628776 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5880. Min Act: -0.0000

Data Index: 124880 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1150253 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5680. Min Act: -0.0000

Data Index: 296688 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5607. Min Act: -0.0000

Data Index: 363053 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1538597 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5060. Min Act: -0.0000

Data Index: 404644 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1461304 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1429143 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4366. Min Act: -0.0000

Data Index: 273249 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5107. Min Act: -0.0000

Data Index: 551788 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5091. Min Act: -0.0000

Data Index: 409975 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1804419 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5335. Min Act: -0.0000

Data Index: 977992 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1393267 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1041562 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4146. Min Act: -0.0000

Data Index: 512843 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4629. Min Act: -0.0000

Data Index: 18986 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1161633 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4356. Min Act: -0.0000

Data Index: 544120 (The Pile)

Max Activating Token Index: 79