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

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

Neuron 665 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.1995. Min Act: -0.0002

Data Index: 617733 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.3698. Min Act: -0.0002

Data Index: 932913 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2290. Min Act: -0.0002

Data Index: 1237940 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.4039. Min Act: -0.0002

Data Index: 716705 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.3438. Min Act: -0.0002

Data Index: 355900 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.1104. Min Act: -0.0002

Data Index: 446674 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2531. Min Act: -0.0002

Data Index: 471124 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2771. Min Act: -0.0002

Data Index: 341077 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2147. Min Act: -0.0002

Data Index: 867480 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2367. Min Act: -0.0002

Data Index: 791938 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2561. Min Act: -0.0002

Data Index: 1060170 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2622. Min Act: -0.0002

Data Index: 857886 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.3392. Min Act: -0.0002

Data Index: 652416 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.3340. Min Act: -0.0002

Data Index: 861741 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.9007. Min Act: -0.0002

Data Index: 934206 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2056. Min Act: -0.0002

Data Index: 196213 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.1645. Min Act: -0.0002

Data Index: 168276 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.1245. Min Act: -0.0002

Data Index: 671691 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.1535. Min Act: -0.0002

Data Index: 520764 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2206. Min Act: -0.0002

Data Index: 439105 (C4 (Web Text))

Max Activating Token Index: 9