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

Dataset: The Pile

Neuron 1651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1606875 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5816. Min Act: -0.0000

Data Index: 573480 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7485. Min Act: -0.0000

Data Index: 461079 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7130. Min Act: 0.0000

Data Index: 144127 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6596. Min Act: -0.0000

Data Index: 707619 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6114. Min Act: 0.0000

Data Index: 442670 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7179. Min Act: -0.0000

Data Index: 663374 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6239. Min Act: 0.0000

Data Index: 1009535 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6734. Min Act: -0.0000

Data Index: 971612 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6613. Min Act: 0.0000

Data Index: 1878216 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1247665 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1142933 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1387197 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6087. Min Act: -0.0000

Data Index: 227040 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6232. Min Act: -0.0000

Data Index: 769758 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7536. Min Act: -0.0000

Data Index: 692923 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1788634 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6131. Min Act: -0.0000

Data Index: 973446 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5680. Min Act: -0.0000

Data Index: 502750 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1236394 (The Pile)

Max Activating Token Index: 209