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

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

Neuron 1616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.8088. Min Act: -0.0000

Data Index: 854650 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6773. Min Act: -0.0001

Data Index: 667445 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6614. Min Act: -0.0001

Data Index: 45557 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1313696 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5930. Min Act: -0.0000

Data Index: 30473 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5552. Min Act: -0.0000

Data Index: 554352 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5782. Min Act: -0.0000

Data Index: 552684 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5497. Min Act: -0.0000

Data Index: 115741 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5454. Min Act: -0.0000

Data Index: 108950 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5437. Min Act: -0.0000

Data Index: 543085 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5203. Min Act: -0.0001

Data Index: 870659 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1143445 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5161. Min Act: -0.0000

Data Index: 388358 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5353. Min Act: -0.0000

Data Index: 563788 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5313. Min Act: -0.0000

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5195. Min Act: -0.0000

Data Index: 342044 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5061. Min Act: -0.0001

Data Index: 412925 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5213. Min Act: -0.0000

Data Index: 12548 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4949. Min Act: -0.0000

Data Index: 892504 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5274. Min Act: -0.0001

Data Index: 339125 (C4 (Web Text))

Max Activating Token Index: 669