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

Dataset: The Pile

Neuron 1944 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: 3.2651. Min Range: -3.2651

Max Act: 3.2651. Min Act: -0.0000

Data Index: 199263 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1854. Min Act: -0.0000

Data Index: 263509 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0801. Min Act: -0.0000

Data Index: 1945664 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2102. Min Act: -0.0000

Data Index: 725990 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0220. Min Act: -0.0000

Data Index: 720372 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0728. Min Act: -0.0000

Data Index: 639177 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0651. Min Act: -0.0000

Data Index: 870733 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.9151. Min Act: -0.0000

Data Index: 1668605 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.6414. Min Act: -0.0000

Data Index: 1681764 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.9001. Min Act: -0.0000

Data Index: 291066 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.8480. Min Act: -0.0000

Data Index: 1549118 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.8186. Min Act: -0.0000

Data Index: 35563 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.8555. Min Act: -0.0000

Data Index: 564874 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.8213. Min Act: -0.0000

Data Index: 269074 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.7010. Min Act: -0.0000

Data Index: 1256473 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.8063. Min Act: -0.0000

Data Index: 921488 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.7820. Min Act: -0.0000

Data Index: 302112 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.6381. Min Act: -0.0000

Data Index: 494439 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1152226 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 3.2651. Min Range: -3.2651

Max Act: 2.5695. Min Act: -0.0000

Data Index: 190572 (The Pile)

Max Activating Token Index: 154