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

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

Neuron 2807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.6021. Min Act: -0.0001

Data Index: 1074350 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5835. Min Act: -0.0001

Data Index: 1188320 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5627. Min Act: -0.0001

Data Index: 1273955 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5438. Min Act: -0.0001

Data Index: 133837 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5541. Min Act: -0.0001

Data Index: 655729 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5323. Min Act: -0.0001

Data Index: 248224 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5180. Min Act: -0.0001

Data Index: 502107 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1025290 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5083. Min Act: -0.0001

Data Index: 580141 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1298152 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5184. Min Act: -0.0001

Data Index: 836455 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5161. Min Act: -0.0001

Data Index: 1069622 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5371. Min Act: -0.0001

Data Index: 865125 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4861. Min Act: -0.0001

Data Index: 381981 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5165. Min Act: -0.0001

Data Index: 897636 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4782. Min Act: -0.0001

Data Index: 599676 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5252. Min Act: -0.0001

Data Index: 1254347 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4925. Min Act: -0.0001

Data Index: 598803 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5512. Min Act: -0.0001

Data Index: 483909 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4878. Min Act: -0.0001

Data Index: 862533 (C4 (Web Text))

Max Activating Token Index: 189