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

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

Neuron 592 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9646. Min Act: -0.0002

Data Index: 1326154 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9700. Min Act: -0.0002

Data Index: 934210 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9690. Min Act: -0.0002

Data Index: 1340876 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9495. Min Act: -0.0002

Data Index: 383685 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9509. Min Act: -0.0002

Data Index: 1187854 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9482. Min Act: -0.0002

Data Index: 213359 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9107. Min Act: -0.0003

Data Index: 1345105 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9078. Min Act: -0.0002

Data Index: 1273912 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8981. Min Act: -0.0002

Data Index: 16808 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9120. Min Act: -0.0002

Data Index: 296208 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8866. Min Act: -0.0002

Data Index: 510321 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9138. Min Act: -0.0002

Data Index: 697427 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8719. Min Act: -0.0002

Data Index: 1082162 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8860. Min Act: -0.0002

Data Index: 482212 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8910. Min Act: -0.0002

Data Index: 892365 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8672. Min Act: -0.0002

Data Index: 745682 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8663. Min Act: -0.0002

Data Index: 152714 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8920. Min Act: -0.0002

Data Index: 327426 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8642. Min Act: -0.0002

Data Index: 347833 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8601. Min Act: -0.0002

Data Index: 89694 (C4 (Web Text))

Max Activating Token Index: 291