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

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

Neuron 42 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: 2.8042. Min Range: -2.8042

Max Act: 2.8042. Min Act: -0.0000

Data Index: 1190097 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.5691. Min Act: -0.0000

Data Index: 760391 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.3613. Min Act: -0.0000

Data Index: 207059 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.3079. Min Act: -0.0000

Data Index: 662218 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.1807. Min Act: -0.0000

Data Index: 519582 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.2676. Min Act: -0.0000

Data Index: 670978 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.2504. Min Act: -0.0000

Data Index: 589162 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.1296. Min Act: -0.0000

Data Index: 705197 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.1685. Min Act: -0.0000

Data Index: 249200 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.1334. Min Act: -0.0000

Data Index: 1003222 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.2146. Min Act: -0.0000

Data Index: 861150 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.0408. Min Act: -0.0000

Data Index: 743718 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.0125. Min Act: -0.0000

Data Index: 761832 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 2.8042. Min Range: -2.8042

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1320238 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.0456. Min Act: -0.0000

Data Index: 214718 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 2.8042. Min Range: -2.8042

Max Act: 1.8191. Min Act: -0.0000

Data Index: 741807 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 2.8042. Min Range: -2.8042

Max Act: 1.8063. Min Act: -0.0000

Data Index: 591423 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 2.8042. Min Range: -2.8042

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1003394 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 2.8042. Min Range: -2.8042

Max Act: 2.0009. Min Act: -0.0000

Data Index: 606083 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 2.8042. Min Range: -2.8042

Max Act: 1.6828. Min Act: -0.0000

Data Index: 63643 (C4 (Web Text))

Max Activating Token Index: 199