Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1951 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5643. Min Range: -3.5643

Max Act: 3.5643. Min Act: -0.0000

Data Index: 1146142 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 3.5643. Min Range: -3.5643

Max Act: 3.0356. Min Act: -0.0000

Data Index: 1001440 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.9858. Min Act: -0.0000

Data Index: 1013747 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.7876. Min Act: -0.0000

Data Index: 896561 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.7935. Min Act: -0.0000

Data Index: 1355815 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.4865. Min Act: -0.0000

Data Index: 936159 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.5135. Min Act: -0.0000

Data Index: 287357 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.5062. Min Act: -0.0000

Data Index: 385113 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.4965. Min Act: -0.0000

Data Index: 549036 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.4817. Min Act: 0.0000

Data Index: 123046 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.3480. Min Act: -0.0000

Data Index: 186791 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.4203. Min Act: -0.0000

Data Index: 1139441 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.3911. Min Act: -0.0000

Data Index: 919140 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.3138. Min Act: -0.0000

Data Index: 87146 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.3169. Min Act: -0.0000

Data Index: 168406 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.1986. Min Act: -0.0000

Data Index: 646264 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.3129. Min Act: -0.0000

Data Index: 665634 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.1576. Min Act: 0.0000

Data Index: 1169854 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.2520. Min Act: 0.0001

Data Index: 547717 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 3.5643. Min Range: -3.5643

Max Act: 2.2358. Min Act: -0.0000

Data Index: 867740 (C4 (Web Text))

Max Activating Token Index: 45