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

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

Neuron 392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7468. Min Act: -0.0002

Data Index: 900455 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1326147 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6081. Min Act: -0.0002

Data Index: 449312 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6251. Min Act: -0.0002

Data Index: 945756 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6139. Min Act: -0.0002

Data Index: 842157 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5885. Min Act: -0.0002

Data Index: 9925 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5712. Min Act: -0.0002

Data Index: 40300 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5542. Min Act: -0.0002

Data Index: 1189736 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5343. Min Act: -0.0002

Data Index: 843820 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5223. Min Act: -0.0002

Data Index: 438978 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5433. Min Act: -0.0001

Data Index: 949303 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6019. Min Act: -0.0002

Data Index: 141406 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5648. Min Act: -0.0002

Data Index: 5198 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5489. Min Act: -0.0001

Data Index: 179274 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5227. Min Act: -0.0002

Data Index: 1110508 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5538. Min Act: -0.0002

Data Index: 826882 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5505. Min Act: -0.0001

Data Index: 461183 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5003. Min Act: -0.0002

Data Index: 443360 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5307. Min Act: -0.0002

Data Index: 1018130 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5249. Min Act: -0.0001

Data Index: 1552050 (Python Code)

Max Activating Token Index: 134