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

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

Neuron 35 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.7855. Min Act: -0.0001

Data Index: 1189493 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.5069. Min Act: -0.0001

Data Index: 162425 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.4336. Min Act: -0.0001

Data Index: 820870 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.3925. Min Act: -0.0001

Data Index: 777592 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.2061. Min Act: -0.0001

Data Index: 854157 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.4254. Min Act: -0.0001

Data Index: 1310207 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.2755. Min Act: -0.0001

Data Index: 989345 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.4560. Min Act: -0.0001

Data Index: 401475 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.1006. Min Act: -0.0001

Data Index: 767956 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.0372. Min Act: -0.0001

Data Index: 27667 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.7855. Min Range: -3.7855

Max Act: 2.9808. Min Act: -0.0001

Data Index: 408574 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.1161. Min Act: -0.0001

Data Index: 13801 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 3.7855. Min Range: -3.7855

Max Act: 2.9628. Min Act: -0.0001

Data Index: 520855 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.0938. Min Act: -0.0001

Data Index: 836375 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.0839. Min Act: -0.0001

Data Index: 1323011 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.0670. Min Act: -0.0001

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.1966. Min Act: -0.0001

Data Index: 377940 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.1833. Min Act: -0.0001

Data Index: 67120 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.3019. Min Act: -0.0001

Data Index: 1119355 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 3.7855. Min Range: -3.7855

Max Act: 3.1340. Min Act: -0.0001

Data Index: 1217631 (C4 (Web Text))

Max Activating Token Index: 93