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

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

Neuron 4849 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1110182 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8400. Min Act: -0.0000

Data Index: 445459 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7284. Min Act: -0.0000

Data Index: 963497 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7523. Min Act: -0.0000

Data Index: 495334 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7484. Min Act: -0.0000

Data Index: 1286058 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6821. Min Act: -0.0000

Data Index: 653736 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7078. Min Act: -0.0000

Data Index: 118397 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1284264 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6880. Min Act: -0.0000

Data Index: 257517 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7893. Min Act: -0.0000

Data Index: 861301 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1045285 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1380066 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6241. Min Act: -0.0000

Data Index: 582147 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5631. Min Act: -0.0000

Data Index: 287195 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5642. Min Act: -0.0000

Data Index: 931146 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5464. Min Act: -0.0000

Data Index: 1229358 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.4964. Min Act: -0.0000

Data Index: 304572 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.4878. Min Act: -0.0000

Data Index: 137283 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5673. Min Act: -0.0000

Data Index: 201854 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5060. Min Act: -0.0000

Data Index: 961564 (C4 (Web Text))

Max Activating Token Index: 983