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

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

Neuron 1981 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7740. Min Range: -4.7740

Max Act: 4.7740. Min Act: -0.0000

Data Index: 1214030 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.4337. Min Act: -0.0000

Data Index: 766047 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.3931. Min Act: 0.0000

Data Index: 160081 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.3570. Min Act: -0.0000

Data Index: 953900 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.2042. Min Act: -0.0000

Data Index: 457828 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.1815. Min Act: -0.0000

Data Index: 816460 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.1703. Min Act: -0.0000

Data Index: 1070302 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9948. Min Act: -0.0000

Data Index: 853222 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9795. Min Act: -0.0000

Data Index: 5722 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1055840 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.0587. Min Act: -0.0000

Data Index: 504874 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9049. Min Act: -0.0000

Data Index: 586681 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 4.7740. Min Range: -4.7740

Max Act: 2.0261. Min Act: -0.0000

Data Index: 656732 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9971. Min Act: -0.0000

Data Index: 144694 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9777. Min Act: -0.0000

Data Index: 85076 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9663. Min Act: 0.0000

Data Index: 462647 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9845. Min Act: -0.0000

Data Index: 726784 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9525. Min Act: 0.0000

Data Index: 315242 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9539. Min Act: -0.0000

Data Index: 458758 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 4.7740. Min Range: -4.7740

Max Act: 1.9531. Min Act: -0.0000

Data Index: 627552 (C4 (Web Text))

Max Activating Token Index: 351