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

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

Neuron 150 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: 0.0697. Min Range: -0.0697

Max Act: 0.0696. Min Act: -0.0002

Data Index: 823925 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0690. Min Act: -0.0002

Data Index: 62497 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0679. Min Act: -0.0002

Data Index: 321220 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0002

Data Index: 200593 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1086252 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0653. Min Act: -0.0002

Data Index: 16606 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0643. Min Act: -0.0002

Data Index: 182968 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0648. Min Act: -0.0002

Data Index: 75938 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1041968 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1157311 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0653. Min Act: -0.0002

Data Index: 121198 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0657. Min Act: -0.0002

Data Index: 611567 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1291195 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0637. Min Act: -0.0002

Data Index: 246845 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0624. Min Act: -0.0002

Data Index: 170528 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0620. Min Act: -0.0002

Data Index: 756456 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0614. Min Act: -0.0002

Data Index: 840678 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0607. Min Act: -0.0002

Data Index: 127062 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0599. Min Act: -0.0002

Data Index: 842114 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1561148 (Python Code)

Max Activating Token Index: 256