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

Dataset: The Pile

Neuron 1319 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.4227. Min Act: 0.0000

Data Index: 1496245 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 5.0153. Min Range: -5.0153

Max Act: 5.0153. Min Act: -0.0000

Data Index: 1063770 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.9979. Min Act: -0.0000

Data Index: 1235900 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.2937. Min Act: -0.0000

Data Index: 380287 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.2191. Min Act: -0.0000

Data Index: 1116841 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.7140. Min Act: -0.0000

Data Index: 421399 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.5781. Min Act: -0.0000

Data Index: 345125 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.9064. Min Act: 0.0000

Data Index: 1162584 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.6349. Min Act: -0.0000

Data Index: 109380 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.3303. Min Act: -0.0000

Data Index: 1683357 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.4549. Min Act: 0.0000

Data Index: 362139 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.6930. Min Act: -0.0000

Data Index: 426920 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.6971. Min Act: -0.0000

Data Index: 1258854 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.0936. Min Act: -0.0000

Data Index: 1342355 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.4180. Min Act: -0.0000

Data Index: 826121 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.6097. Min Act: -0.0000

Data Index: 1376276 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.1456. Min Act: -0.0000

Data Index: 1563642 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.0738. Min Act: -0.0000

Data Index: 667423 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.4680. Min Act: -0.0000

Data Index: 907452 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 5.0153. Min Range: -5.0153

Max Act: 3.3865. Min Act: -0.0000

Data Index: 1990549 (The Pile)

Max Activating Token Index: 505