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

Dataset: The Pile

Neuron 2707 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: 1.7585. Min Range: -1.7585

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1091389 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.6226. Min Act: -0.0000

Data Index: 970361 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1008288 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.6574. Min Act: -0.0000

Data Index: 1016082 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.6195. Min Act: -0.0000

Data Index: 1190563 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.7286. Min Act: -0.0000

Data Index: 69497 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.6285. Min Act: -0.0000

Data Index: 122924 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1211283 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1479721 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.6657. Min Act: -0.0000

Data Index: 229100 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.5140. Min Act: -0.0000

Data Index: 1389025 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1363549 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1486743 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1386472 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.5704. Min Act: -0.0000

Data Index: 1907231 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1150046 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.4136. Min Act: -0.0000

Data Index: 489770 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1851015 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1455856 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 1.7585. Min Range: -1.7585

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1627790 (The Pile)

Max Activating Token Index: 182