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

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

Neuron 800 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: 5.0019. Min Range: -5.0019

Max Act: 5.0019. Min Act: -0.0001

Data Index: 799941 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6691. Min Act: -0.0001

Data Index: 988355 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.3869. Min Act: -0.0001

Data Index: 34342 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6479. Min Act: -0.0001

Data Index: 1139707 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.3224. Min Act: -0.0001

Data Index: 1106406 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.1920. Min Act: -0.0001

Data Index: 89954 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.4313. Min Act: -0.0001

Data Index: 774828 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.0723. Min Act: -0.0001

Data Index: 677227 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.0534. Min Act: -0.0001

Data Index: 31997 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.0981. Min Act: -0.0002

Data Index: 1053237 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.0663. Min Act: -0.0001

Data Index: 527299 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.0848. Min Act: -0.0001

Data Index: 1124519 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.8835. Min Act: -0.0001

Data Index: 288247 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.8468. Min Act: -0.0002

Data Index: 994105 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.8713. Min Act: -0.0001

Data Index: 1067777 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.9302. Min Act: -0.0002

Data Index: 951172 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.7813. Min Act: -0.0001

Data Index: 1000611 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.7305. Min Act: -0.0002

Data Index: 382820 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.7395. Min Act: -0.0001

Data Index: 691525 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 5.0019. Min Range: -5.0019

Max Act: 3.7288. Min Act: -0.0001

Data Index: 819437 (C4 (Web Text))

Max Activating Token Index: 103