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

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

Neuron 3489 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4700. Min Act: -0.0000

Data Index: 545973 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3796. Min Act: -0.0000

Data Index: 533010 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3520. Min Act: -0.0000

Data Index: 726801 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3437. Min Act: -0.0000

Data Index: 62764 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3132. Min Act: -0.0000

Data Index: 82356 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3608. Min Act: -0.0000

Data Index: 71594 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3237. Min Act: -0.0000

Data Index: 988175 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1277692 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2988. Min Act: -0.0000

Data Index: 552057 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3157. Min Act: -0.0000

Data Index: 881682 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2878. Min Act: -0.0000

Data Index: 389276 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1187368 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2313. Min Act: -0.0000

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2814. Min Act: -0.0000

Data Index: 669899 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1170769 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2673. Min Act: -0.0000

Data Index: 871708 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2897. Min Act: -0.0000

Data Index: 187288 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2381. Min Act: -0.0000

Data Index: 953345 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2402. Min Act: -0.0000

Data Index: 345932 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1106583 (C4 (Web Text))

Max Activating Token Index: 750