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

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

Neuron 3240 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.4596. Min Act: -0.0002

Data Index: 269499 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.3141. Min Act: -0.0002

Data Index: 398802 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.3196. Min Act: -0.0001

Data Index: 544942 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.3315. Min Act: -0.0001

Data Index: 599995 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.2334. Min Act: -0.0001

Data Index: 518568 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.2332. Min Act: -0.0001

Data Index: 558118 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.2210. Min Act: -0.0001

Data Index: 806019 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.2666. Min Act: -0.0002

Data Index: 1151165 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.1410. Min Act: -0.0002

Data Index: 170638 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.2403. Min Act: -0.0002

Data Index: 211205 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.0057. Min Act: -0.0002

Data Index: 817275 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.1595. Min Act: -0.0002

Data Index: 999389 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.4596. Min Range: -1.4596

Max Act: 0.8934. Min Act: -0.0001

Data Index: 225520 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.0871. Min Act: -0.0001

Data Index: 292381 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.0931. Min Act: -0.0001

Data Index: 230285 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.4596. Min Range: -1.4596

Max Act: 0.9869. Min Act: -0.0001

Data Index: 708345 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.4596. Min Range: -1.4596

Max Act: 0.9871. Min Act: -0.0001

Data Index: 1023624 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.4596. Min Range: -1.4596

Max Act: 1.0389. Min Act: -0.0001

Data Index: 615454 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.4596. Min Range: -1.4596

Max Act: 0.8916. Min Act: -0.0002

Data Index: 705455 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.4596. Min Range: -1.4596

Max Act: 0.9905. Min Act: -0.0001

Data Index: 524700 (C4 (Web Text))

Max Activating Token Index: 611