Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 860 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3893. Min Act: -0.0001

Data Index: 1166082 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9589. Min Act: -0.0001

Data Index: 971864 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8971. Min Act: -0.0001

Data Index: 737091 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8703. Min Act: -0.0001

Data Index: 675301 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8212. Min Act: -0.0001

Data Index: 693526 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7670. Min Act: -0.0001

Data Index: 194712 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7979. Min Act: -0.0001

Data Index: 864978 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8423. Min Act: -0.0001

Data Index: 898599 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.6977. Min Act: -0.0001

Data Index: 301460 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7897. Min Act: -0.0001

Data Index: 868192 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7869. Min Act: -0.0001

Data Index: 1251079 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7813. Min Act: -0.0001

Data Index: 483756 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8193. Min Act: -0.0001

Data Index: 37663 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7149. Min Act: -0.0001

Data Index: 572590 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1216303 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7449. Min Act: -0.0001

Data Index: 618350 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1297130 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.6900. Min Act: -0.0001

Data Index: 238243 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.6920. Min Act: -0.0001

Data Index: 999688 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.7127. Min Act: -0.0001

Data Index: 940820 (C4 (Web Text))

Max Activating Token Index: 574