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

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

Neuron 290 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: 0.7200. Min Range: -0.7200

Max Act: 0.7200. Min Act: -0.0001

Data Index: 776439 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5706. Min Act: -0.0001

Data Index: 1139929 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1095085 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4723. Min Act: -0.0001

Data Index: 1145934 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4989. Min Act: -0.0001

Data Index: 924736 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1202221 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4891. Min Act: -0.0001

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4877. Min Act: -0.0001

Data Index: 998376 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1182388 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5186. Min Act: -0.0001

Data Index: 861759 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4865. Min Act: -0.0001

Data Index: 36948 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4830. Min Act: -0.0001

Data Index: 628851 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4860. Min Act: -0.0001

Data Index: 107092 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4435. Min Act: -0.0001

Data Index: 405899 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4576. Min Act: -0.0001

Data Index: 197858 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4388. Min Act: -0.0001

Data Index: 525991 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4934. Min Act: -0.0001

Data Index: 323922 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4624. Min Act: -0.0001

Data Index: 1297559 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4510. Min Act: -0.0001

Data Index: 265980 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4772. Min Act: -0.0001

Data Index: 214567 (C4 (Web Text))

Max Activating Token Index: 482