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

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

Neuron 2223 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: 0.6739. Min Range: -0.6739

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1080480 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6739. Min Act: -0.0001

Data Index: 926861 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5841. Min Act: -0.0001

Data Index: 413095 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5430. Min Act: -0.0001

Data Index: 311078 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5471. Min Act: -0.0001

Data Index: 382124 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5387. Min Act: -0.0001

Data Index: 399731 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5527. Min Act: -0.0001

Data Index: 119211 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5489. Min Act: -0.0001

Data Index: 530236 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5195. Min Act: -0.0001

Data Index: 655227 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5052. Min Act: -0.0001

Data Index: 885956 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5236. Min Act: -0.0001

Data Index: 526349 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4974. Min Act: -0.0001

Data Index: 120993 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5487. Min Act: -0.0001

Data Index: 69568 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4955. Min Act: -0.0001

Data Index: 389135 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4898. Min Act: -0.0001

Data Index: 650619 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5070. Min Act: -0.0001

Data Index: 349353 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4849. Min Act: -0.0001

Data Index: 232211 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5150. Min Act: -0.0001

Data Index: 103717 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4951. Min Act: -0.0001

Data Index: 1147689 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5199. Min Act: -0.0001

Data Index: 120983 (C4 (Web Text))

Max Activating Token Index: 649