Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1349235 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.2554. Min Act: -0.0001

Data Index: 836792 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0842. Min Act: -0.0000

Data Index: 916670 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.1219. Min Act: -0.0001

Data Index: 1180002 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9801. Min Act: -0.0001

Data Index: 831591 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0679. Min Act: -0.0001

Data Index: 1087670 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9568. Min Act: -0.0000

Data Index: 43695 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1024440 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9942. Min Act: -0.0001

Data Index: 1258860 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0618. Min Act: -0.0001

Data Index: 35995 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9135. Min Act: -0.0000

Data Index: 977561 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9588. Min Act: -0.0000

Data Index: 137831 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9598. Min Act: -0.0000

Data Index: 945703 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9529. Min Act: -0.0000

Data Index: 411519 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.8958. Min Act: -0.0001

Data Index: 228845 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.8088. Min Act: -0.0001

Data Index: 1188069 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.8605. Min Act: -0.0001

Data Index: 716555 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1281439 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.8787. Min Act: -0.0000

Data Index: 673830 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9043. Min Act: -0.0000

Data Index: 192816 (C4 (Web Text))

Max Activating Token Index: 605