Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1103 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.5982. Min Act: -0.0001

Data Index: 683829 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4828. Min Act: -0.0001

Data Index: 756978 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3922. Min Act: -0.0001

Data Index: 656343 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4299. Min Act: -0.0001

Data Index: 842474 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4542. Min Act: -0.0001

Data Index: 140046 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3961. Min Act: -0.0001

Data Index: 397561 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4105. Min Act: -0.0001

Data Index: 373454 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4092. Min Act: -0.0001

Data Index: 239425 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1355298 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3581. Min Act: -0.0001

Data Index: 215401 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3861. Min Act: -0.0001

Data Index: 897260 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3657. Min Act: -0.0001

Data Index: 290933 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3601. Min Act: -0.0001

Data Index: 30505 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1305707 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1227801 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3126. Min Act: -0.0001

Data Index: 493561 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3475. Min Act: -0.0001

Data Index: 648000 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3175. Min Act: -0.0001

Data Index: 144848 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3640. Min Act: -0.0001

Data Index: 571360 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1339930 (C4 (Web Text))

Max Activating Token Index: 402