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

Dataset: The Pile

Neuron 5035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1429449 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5272. Min Act: -0.0000

Data Index: 707811 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1955087 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1598780 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4639. Min Act: -0.0000

Data Index: 160711 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4267. Min Act: -0.0000

Data Index: 362132 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1268638 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1342831 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1491236 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4051. Min Act: -0.0000

Data Index: 122419 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4300. Min Act: -0.0000

Data Index: 796609 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1054460 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4050. Min Act: -0.0000

Data Index: 657920 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4424. Min Act: -0.0000

Data Index: 763878 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3404. Min Act: -0.0000

Data Index: 7290 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3167. Min Act: -0.0000

Data Index: 767321 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1505752 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3981. Min Act: -0.0000

Data Index: 962481 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1470004 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1334842 (The Pile)

Max Activating Token Index: 537