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

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

Neuron 4269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1284816 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.7844. Min Act: -0.0000

Data Index: 106682 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1224847 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5609. Min Act: -0.0000

Data Index: 407985 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5502. Min Act: -0.0000

Data Index: 352381 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5113. Min Act: -0.0000

Data Index: 650871 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1174693 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5059. Min Act: -0.0000

Data Index: 89772 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4698. Min Act: -0.0000

Data Index: 366814 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1109280 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4722. Min Act: -0.0000

Data Index: 490047 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4578. Min Act: -0.0000

Data Index: 205666 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1493767 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1549065 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4390. Min Act: -0.0000

Data Index: 268808 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4170. Min Act: -0.0000

Data Index: 698695 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4386. Min Act: -0.0000

Data Index: 121859 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.3971. Min Act: -0.0000

Data Index: 286313 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.4009. Min Act: -0.0000

Data Index: 782439 (C4 (Web Text))

Max Activating Token Index: 110