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

Dataset: The Pile

Neuron 5080 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: 5.8043. Min Range: -5.8043

Max Act: 5.8043. Min Act: -0.0000

Data Index: 878680 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.7507. Min Act: -0.0000

Data Index: 1329995 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.0159. Min Act: -0.0000

Data Index: 1872320 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.0081. Min Act: -0.0000

Data Index: 1313064 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.7158. Min Act: -0.0000

Data Index: 48482 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.0722. Min Act: -0.0000

Data Index: 1816802 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.8659. Min Act: -0.0000

Data Index: 1716150 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.8362. Min Act: -0.0000

Data Index: 1778261 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.6215. Min Act: -0.0000

Data Index: 1541109 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.5758. Min Act: -0.0000

Data Index: 707998 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.6998. Min Act: -0.0000

Data Index: 1907089 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.6451. Min Act: -0.0000

Data Index: 459935 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.7937. Min Act: -0.0000

Data Index: 723499 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.6080. Min Act: -0.0000

Data Index: 1739517 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.5755. Min Act: -0.0000

Data Index: 1320457 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.5560. Min Act: -0.0000

Data Index: 1361974 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.5717. Min Act: -0.0000

Data Index: 257921 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.5317. Min Act: -0.0000

Data Index: 812832 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.3414. Min Act: -0.0000

Data Index: 1870148 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 5.8043. Min Range: -5.8043

Max Act: 4.4559. Min Act: -0.0000

Data Index: 1008137 (The Pile)

Max Activating Token Index: 745