Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 649 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5328. Min Act: -0.0001

Data Index: 118446 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1187673 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5063. Min Act: -0.0001

Data Index: 510883 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4724. Min Act: -0.0001

Data Index: 75970 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4492. Min Act: -0.0001

Data Index: 14255 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4301. Min Act: -0.0001

Data Index: 58851 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4011. Min Act: -0.0001

Data Index: 512158 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4261. Min Act: -0.0001

Data Index: 973562 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3591. Min Act: -0.0001

Data Index: 411320 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3961. Min Act: -0.0001

Data Index: 794650 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4170. Min Act: -0.0000

Data Index: 941651 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4029. Min Act: -0.0001

Data Index: 183802 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1352554 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3370. Min Act: -0.0001

Data Index: 685173 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3894. Min Act: -0.0000

Data Index: 963148 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3658. Min Act: -0.0001

Data Index: 229015 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3599. Min Act: 0.0000

Data Index: 123864 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3711. Min Act: -0.0001

Data Index: 275380 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3680. Min Act: -0.0001

Data Index: 601597 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3632. Min Act: -0.0001

Data Index: 481475 (C4 (Web Text))

Max Activating Token Index: 165