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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 612 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1931. Min Act: -0.0000

Data Index: 720351 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9983. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0062. Min Act: -0.0000

Data Index: 364747 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1009922 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8270. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8057. Min Act: -0.0000

Data Index: 219846 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1282089 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8255. Min Act: -0.0000

Data Index: 420452 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8377. Min Act: -0.0000

Data Index: 482779 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8153. Min Act: -0.0000

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7920. Min Act: -0.0000

Data Index: 335864 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7821. Min Act: -0.0000

Data Index: 192500 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.6889. Min Act: -0.0000

Data Index: 166563 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.6471. Min Act: -0.0000

Data Index: 709528 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7521. Min Act: -0.0000

Data Index: 596294 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7651. Min Act: -0.0000

Data Index: 73709 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7187. Min Act: -0.0000

Data Index: 384686 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1083566 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7093. Min Act: -0.0000

Data Index: 397335 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7323. Min Act: -0.0000

Data Index: 714522 (C4 (Web Text))

Max Activating Token Index: 104