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

Dataset: The Pile

Neuron 2217 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.7001. Min Act: -0.0000

Data Index: 416212 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1292343 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1667105 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.7053. Min Act: -0.0000

Data Index: 440361 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1115694 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6523. Min Act: -0.0000

Data Index: 192651 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1414108 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1764648 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1311898 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1552323 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5370. Min Act: -0.0000

Data Index: 772774 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6433. Min Act: -0.0000

Data Index: 700739 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1444814 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1112415 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6592. Min Act: -0.0000

Data Index: 312742 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6066. Min Act: -0.0000

Data Index: 160540 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5253. Min Act: -0.0000

Data Index: 926302 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1910964 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1971299 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1588625 (The Pile)

Max Activating Token Index: 797