Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1020 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5543. Min Range: -4.5543

Max Act: 4.1975. Min Act: -0.0000

Data Index: 1491703 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.9044. Min Act: -0.0000

Data Index: 1179645 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 4.5543. Min Range: -4.5543

Max Act: 4.2267. Min Act: -0.0000

Data Index: 108878 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 4.5543. Min Range: -4.5543

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1476414 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.9337. Min Act: -0.0000

Data Index: 1128546 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6949. Min Act: -0.0000

Data Index: 891960 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.8292. Min Act: -0.0000

Data Index: 862663 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.9627. Min Act: -0.0000

Data Index: 1192758 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.2999. Min Act: -0.0000

Data Index: 1576526 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.8694. Min Act: -0.0000

Data Index: 861724 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6617. Min Act: -0.0000

Data Index: 9883 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6779. Min Act: -0.0000

Data Index: 386694 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6174. Min Act: -0.0000

Data Index: 806453 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.4565. Min Act: -0.0000

Data Index: 354247 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6622. Min Act: -0.0000

Data Index: 1357180 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.6169. Min Act: -0.0000

Data Index: 941139 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.7713. Min Act: -0.0000

Data Index: 132109 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.5864. Min Act: -0.0000

Data Index: 780023 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 4.5543. Min Range: -4.5543

Max Act: 4.1839. Min Act: -0.0000

Data Index: 554152 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 4.5543. Min Range: -4.5543

Max Act: 3.7092. Min Act: -0.0000

Data Index: 922135 (C4 (Web Text))

Max Activating Token Index: 727