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

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

Neuron 906 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: 0.8523. Min Range: -0.8523

Max Act: 0.8107. Min Act: -0.0002

Data Index: 307927 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8109. Min Act: -0.0002

Data Index: 1302249 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7851. Min Act: -0.0001

Data Index: 1002816 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8437. Min Act: -0.0002

Data Index: 203803 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8450. Min Act: -0.0002

Data Index: 84245 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8048. Min Act: -0.0002

Data Index: 464324 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8267. Min Act: -0.0001

Data Index: 640059 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8523. Min Act: -0.0002

Data Index: 102220 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8152. Min Act: -0.0001

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7791. Min Act: -0.0001

Data Index: 66482 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8028. Min Act: -0.0002

Data Index: 309203 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8264. Min Act: -0.0002

Data Index: 466533 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7077. Min Act: -0.0001

Data Index: 1037290 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7751. Min Act: -0.0001

Data Index: 469498 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8191. Min Act: -0.0001

Data Index: 1286353 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7720. Min Act: -0.0002

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1113609 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8157. Min Act: -0.0002

Data Index: 1059991 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8140. Min Act: -0.0001

Data Index: 671707 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6725. Min Act: -0.0001

Data Index: 490221 (C4 (Web Text))

Max Activating Token Index: 757