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

Dataset: The Pile

Neuron 3799 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: 3.8127. Min Range: -3.8127

Max Act: 3.7547. Min Act: -0.0000

Data Index: 1259050 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.8127. Min Act: -0.0000

Data Index: 1186577 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.3643. Min Act: -0.0000

Data Index: 101133 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.2864. Min Act: -0.0000

Data Index: 1269873 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5060. Min Act: -0.0000

Data Index: 344336 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.2760. Min Act: -0.0000

Data Index: 1192821 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.0040. Min Act: -0.0000

Data Index: 316995 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.1312. Min Act: -0.0000

Data Index: 732606 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.1180. Min Act: -0.0000

Data Index: 889367 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.1018. Min Act: -0.0000

Data Index: 1212521 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.8440. Min Act: -0.0000

Data Index: 1892010 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.7596. Min Act: -0.0000

Data Index: 1485853 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.0645. Min Act: -0.0000

Data Index: 943560 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.9430. Min Act: -0.0000

Data Index: 1011103 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.8960. Min Act: -0.0000

Data Index: 1826344 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.7815. Min Act: -0.0000

Data Index: 1031178 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.7857. Min Act: -0.0000

Data Index: 1973044 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.6423. Min Act: -0.0000

Data Index: 113388 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.6092. Min Act: -0.0000

Data Index: 693718 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 3.8127. Min Range: -3.8127

Max Act: 2.8664. Min Act: -0.0000

Data Index: 859625 (The Pile)

Max Activating Token Index: 317