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

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

Neuron 3010 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1452. Min Range: -1.1452

Max Act: 1.1452. Min Act: -0.0000

Data Index: 573844 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8274. Min Act: 0.0000

Data Index: 901587 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8008. Min Act: -0.0000

Data Index: 864071 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7790. Min Act: 0.0000

Data Index: 586431 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1029248 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7076. Min Act: 0.0000

Data Index: 265956 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7335. Min Act: -0.0000

Data Index: 216300 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7337. Min Act: 0.0000

Data Index: 971925 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7197. Min Act: -0.0000

Data Index: 754074 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7085. Min Act: 0.0000

Data Index: 1143124 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7490. Min Act: -0.0000

Data Index: 697474 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7356. Min Act: -0.0000

Data Index: 650329 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6823. Min Act: -0.0000

Data Index: 564330 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.7191. Min Act: -0.0000

Data Index: 200429 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6683. Min Act: -0.0000

Data Index: 637850 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6271. Min Act: -0.0000

Data Index: 426057 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6646. Min Act: -0.0000

Data Index: 762035 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6610. Min Act: 0.0000

Data Index: 1272502 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6419. Min Act: 0.0000

Data Index: 1314510 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.6231. Min Act: -0.0000

Data Index: 286157 (C4 (Web Text))

Max Activating Token Index: 19