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

Dataset: The Pile

Neuron 216 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.8051. Min Act: 0.0000

Data Index: 562074 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1107326 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1417504 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1608565 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1400387 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1154566 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1810896 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5533. Min Act: -0.0000

Data Index: 168512 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1651805 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5461. Min Act: -0.0000

Data Index: 141668 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5461. Min Act: -0.0000

Data Index: 662209 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1444392 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1589440 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.4964. Min Act: -0.0000

Data Index: 676676 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1731985 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5173. Min Act: -0.0000

Data Index: 142189 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5485. Min Act: -0.0000

Data Index: 321674 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1697765 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.4927. Min Act: -0.0000

Data Index: 214147 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5346. Min Act: -0.0000

Data Index: 937206 (The Pile)

Max Activating Token Index: 894