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

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

Neuron 2575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.5278. Min Act: -0.0000

Data Index: 859483 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.2920. Min Act: -0.0000

Data Index: 1067383 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.5067. Min Act: -0.0000

Data Index: 621746 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.3763. Min Act: -0.0000

Data Index: 507012 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.3335. Min Act: -0.0000

Data Index: 578152 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1172201 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.2120. Min Act: -0.0000

Data Index: 311491 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.3447. Min Act: -0.0000

Data Index: 13925 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.3127. Min Act: -0.0000

Data Index: 1031453 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1764. Min Act: -0.0000

Data Index: 595137 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1531. Min Act: -0.0000

Data Index: 562068 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1445. Min Act: -0.0000

Data Index: 875781 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1339. Min Act: -0.0000

Data Index: 585283 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1239. Min Act: -0.0000

Data Index: 1456064 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1004446 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.5278. Min Range: -2.5278

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1388441 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.0616. Min Act: -0.0000

Data Index: 751643 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.0621. Min Act: -0.0000

Data Index: 588989 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1240317 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 2.5278. Min Range: -2.5278

Max Act: 2.0099. Min Act: -0.0000

Data Index: 872718 (C4 (Web Text))

Max Activating Token Index: 624