Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2338 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6500. Min Act: -0.0001

Data Index: 1319214 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5852. Min Act: -0.0001

Data Index: 1346128 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6015. Min Act: -0.0001

Data Index: 329065 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1150726 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1152725 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6199. Min Act: -0.0001

Data Index: 248863 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6138. Min Act: -0.0001

Data Index: 98092 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5675. Min Act: -0.0001

Data Index: 414096 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6076. Min Act: -0.0001

Data Index: 453042 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6277. Min Act: -0.0001

Data Index: 738180 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5630. Min Act: -0.0001

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5779. Min Act: -0.0001

Data Index: 956535 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5082. Min Act: -0.0001

Data Index: 692201 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5579. Min Act: -0.0001

Data Index: 1330210 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5034. Min Act: -0.0001

Data Index: 615974 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5584. Min Act: -0.0001

Data Index: 912617 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1090933 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5207. Min Act: -0.0001

Data Index: 1350393 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5672. Min Act: -0.0001

Data Index: 336607 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5103. Min Act: -0.0001

Data Index: 365570 (C4 (Web Text))

Max Activating Token Index: 90