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

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

Neuron 788 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.6036. Min Act: -0.0000

Data Index: 1376543 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1544014 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.4107. Min Act: -0.0000

Data Index: 1570105 (Python Code)

Max Activating Token Index: 426

Text #3

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.2179. Min Act: -0.0000

Data Index: 1610380 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.2105. Min Act: -0.0000

Data Index: 1363208 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 2.6036. Min Range: -2.6036

Max Act: 2.0792. Min Act: -0.0000

Data Index: 1435229 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.9440. Min Act: -0.0000

Data Index: 1510286 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1393855 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.9865. Min Act: -0.0000

Data Index: 1332438 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1254313 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1400957 (Python Code)

Max Activating Token Index: 288

Text #11

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1640671 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.6677. Min Act: -0.0000

Data Index: 80647 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1461410 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7867. Min Act: -0.0000

Data Index: 1610389 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.9969. Min Act: -0.0000

Data Index: 1230926 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.6738. Min Act: -0.0000

Data Index: 1546977 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.6541. Min Act: -0.0000

Data Index: 1629657 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1482386 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 2.6036. Min Range: -2.6036

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1503307 (Python Code)

Max Activating Token Index: 213