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

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

Neuron 4106 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: 0.3367. Min Range: -0.3367

Max Act: 0.3367. Min Act: -0.0002

Data Index: 1415533 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3191. Min Act: -0.0002

Data Index: 1592314 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3176. Min Act: -0.0002

Data Index: 1462691 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3109. Min Act: -0.0002

Data Index: 1373744 (Python Code)

Max Activating Token Index: 459

Text #4

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3158. Min Act: -0.0003

Data Index: 507837 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3137. Min Act: -0.0002

Data Index: 1243573 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2991. Min Act: -0.0002

Data Index: 1483193 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3057. Min Act: -0.0002

Data Index: 1644605 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.3061. Min Act: -0.0002

Data Index: 1232872 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2843. Min Act: -0.0002

Data Index: 1631542 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2884. Min Act: -0.0002

Data Index: 1309150 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2797. Min Act: -0.0002

Data Index: 1362198 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2708. Min Act: -0.0003

Data Index: 176032 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2773. Min Act: -0.0002

Data Index: 1454599 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2792. Min Act: -0.0003

Data Index: 680178 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2735. Min Act: -0.0003

Data Index: 841998 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2612. Min Act: -0.0002

Data Index: 1100934 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2643. Min Act: -0.0002

Data Index: 1457049 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2673. Min Act: -0.0002

Data Index: 1517001 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2658. Min Act: -0.0002

Data Index: 227704 (C4 (Web Text))

Max Activating Token Index: 962