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

Dataset: The Pile

Neuron 3122 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1118956 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4446. Min Act: -0.0000

Data Index: 733097 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4659. Min Act: -0.0000

Data Index: 619320 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1575915 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1446916 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1207668 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4121. Min Act: -0.0000

Data Index: 400958 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4218. Min Act: -0.0000

Data Index: 59900 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4312. Min Act: -0.0000

Data Index: 402593 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1121254 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4170. Min Act: -0.0000

Data Index: 589282 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3735. Min Act: -0.0000

Data Index: 153252 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3957. Min Act: -0.0000

Data Index: 138197 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1767507 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3804. Min Act: -0.0000

Data Index: 192801 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1990922 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1539896 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1552957 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1378378 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3884. Min Act: -0.0000

Data Index: 229732 (The Pile)

Max Activating Token Index: 393