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

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

Neuron 3777 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0303. Min Range: -1.0303

Max Act: 1.0303. Min Act: -0.0000

Data Index: 678401 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.7176. Min Act: -0.0001

Data Index: 288360 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.7182. Min Act: -0.0000

Data Index: 526182 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1345395 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6961. Min Act: -0.0001

Data Index: 322620 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6255. Min Act: -0.0000

Data Index: 493372 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6272. Min Act: -0.0001

Data Index: 1269799 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6248. Min Act: -0.0000

Data Index: 38567 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6224. Min Act: -0.0001

Data Index: 51964 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5964. Min Act: -0.0000

Data Index: 367457 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6080. Min Act: -0.0001

Data Index: 42242 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.6212. Min Act: -0.0000

Data Index: 341638 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5671. Min Act: -0.0001

Data Index: 760600 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5776. Min Act: -0.0000

Data Index: 668282 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5794. Min Act: -0.0001

Data Index: 158778 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1104016 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5846. Min Act: -0.0000

Data Index: 644452 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5262. Min Act: -0.0000

Data Index: 167467 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5440. Min Act: -0.0000

Data Index: 186512 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.0303. Min Range: -1.0303

Max Act: 0.5533. Min Act: -0.0001

Data Index: 648343 (C4 (Web Text))

Max Activating Token Index: 942