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

Dataset: The Pile

Neuron 4787 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: 5.1339. Min Range: -5.1339

Max Act: 5.1339. Min Act: -0.0000

Data Index: 1909820 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.3176. Min Act: -0.0000

Data Index: 449715 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4167. Min Act: -0.0000

Data Index: 1419910 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.7462. Min Act: -0.0000

Data Index: 685387 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4309. Min Act: -0.0000

Data Index: 1590626 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.5593. Min Act: -0.0000

Data Index: 1258465 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2311. Min Act: -0.0000

Data Index: 1980609 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2063. Min Act: -0.0000

Data Index: 894103 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.1760. Min Act: -0.0000

Data Index: 1094341 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2747. Min Act: -0.0000

Data Index: 210432 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.0939. Min Act: -0.0000

Data Index: 1657081 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.0626. Min Act: -0.0000

Data Index: 740092 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.1922. Min Act: -0.0000

Data Index: 1909702 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.0127. Min Act: -0.0000

Data Index: 1593088 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 5.1339. Min Range: -5.1339

Max Act: 2.8383. Min Act: -0.0000

Data Index: 1757550 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.0322. Min Act: -0.0000

Data Index: 809166 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.1991. Min Act: -0.0000

Data Index: 1956590 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 5.1339. Min Range: -5.1339

Max Act: 2.6619. Min Act: -0.0000

Data Index: 141606 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 5.1339. Min Range: -5.1339

Max Act: 2.7915. Min Act: -0.0000

Data Index: 1846554 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 5.1339. Min Range: -5.1339

Max Act: 2.9064. Min Act: -0.0000

Data Index: 532897 (The Pile)

Max Activating Token Index: 1019