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

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

Neuron 1550 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9621. Min Act: -0.0002

Data Index: 18091 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9621. Min Act: -0.0002

Data Index: 363403 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9408. Min Act: -0.0002

Data Index: 1284631 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9252. Min Act: -0.0002

Data Index: 269529 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9290. Min Act: -0.0002

Data Index: 1304828 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9211. Min Act: -0.0002

Data Index: 966187 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9110. Min Act: -0.0002

Data Index: 86576 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9139. Min Act: -0.0002

Data Index: 646452 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9162. Min Act: -0.0002

Data Index: 1563119 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8758. Min Act: -0.0002

Data Index: 786430 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9065. Min Act: -0.0002

Data Index: 1065611 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8881. Min Act: -0.0002

Data Index: 252861 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8736. Min Act: -0.0002

Data Index: 1027094 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8544. Min Act: -0.0002

Data Index: 16064 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8796. Min Act: -0.0002

Data Index: 757091 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8609. Min Act: -0.0002

Data Index: 1259092 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8723. Min Act: -0.0002

Data Index: 1242438 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8599. Min Act: -0.0002

Data Index: 376764 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8671. Min Act: -0.0002

Data Index: 1298069 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8747. Min Act: -0.0002

Data Index: 1179582 (C4 (Web Text))

Max Activating Token Index: 50