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

Dataset: The Pile

Neuron 2015 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: 1.1734. Min Range: -1.1734

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1490763 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0106. Min Act: -0.0000

Data Index: 367516 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0697. Min Act: -0.0000

Data Index: 633873 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0457. Min Act: -0.0000

Data Index: 735168 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0049. Min Act: -0.0000

Data Index: 823800 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1688205 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1101. Min Act: -0.0000

Data Index: 802971 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1624582 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1533068 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1181481 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1513151 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9463. Min Act: -0.0000

Data Index: 718721 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1107612 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1778235 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1887429 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8839. Min Act: -0.0000

Data Index: 896252 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9872. Min Act: 0.0000

Data Index: 1377492 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8715. Min Act: -0.0000

Data Index: 166702 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9336. Min Act: -0.0000

Data Index: 956654 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8547. Min Act: -0.0000

Data Index: 321197 (The Pile)

Max Activating Token Index: 594