Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7593. Min Act: -0.0001

Data Index: 43258 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.8027. Min Act: -0.0001

Data Index: 1081393 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6932. Min Act: -0.0001

Data Index: 242500 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6570. Min Act: -0.0001

Data Index: 221647 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7478. Min Act: -0.0001

Data Index: 241866 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7164. Min Act: -0.0001

Data Index: 233622 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1123336 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6555. Min Act: -0.0001

Data Index: 837754 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6043. Min Act: -0.0001

Data Index: 83466 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6048. Min Act: -0.0001

Data Index: 100533 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6051. Min Act: -0.0001

Data Index: 409663 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6488. Min Act: -0.0001

Data Index: 384963 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6516. Min Act: -0.0001

Data Index: 475609 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1262335 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5853. Min Act: -0.0001

Data Index: 91884 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5920. Min Act: -0.0001

Data Index: 637336 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5790. Min Act: -0.0001

Data Index: 1355419 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1289612 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1141422 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5381. Min Act: -0.0001

Data Index: 14082 (C4 (Web Text))

Max Activating Token Index: 173