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

Dataset: The Pile

Neuron 3905 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: 1.3649. Min Range: -1.3649

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1344163 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.1735. Min Act: -0.0000

Data Index: 906690 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1191088 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.2438. Min Act: -0.0000

Data Index: 149650 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0855. Min Act: -0.0000

Data Index: 556111 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1123824 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1061016 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1546068 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0521. Min Act: -0.0000

Data Index: 44457 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0072. Min Act: -0.0000

Data Index: 25474 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.1501. Min Act: -0.0000

Data Index: 382534 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9358. Min Act: -0.0000

Data Index: 466121 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1605523 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1322594 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9170. Min Act: -0.0000

Data Index: 364149 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9919. Min Act: -0.0000

Data Index: 111819 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9919. Min Act: -0.0000

Data Index: 765199 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1154579 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1158250 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1548912 (The Pile)

Max Activating Token Index: 721