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

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

Neuron 280 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: 1.3788. Min Range: -1.3788

Max Act: 1.3788. Min Act: -0.0002

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.3618. Min Act: -0.0002

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.3052. Min Act: -0.0002

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2522. Min Act: -0.0002

Data Index: 338568 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2746. Min Act: -0.0002

Data Index: 1193274 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2282. Min Act: -0.0002

Data Index: 355129 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2241. Min Act: -0.0002

Data Index: 222854 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2118. Min Act: -0.0002

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1806. Min Act: -0.0002

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2094. Min Act: -0.0002

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1969. Min Act: -0.0002

Data Index: 150368 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1885. Min Act: -0.0002

Data Index: 205844 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1797. Min Act: -0.0002

Data Index: 245620 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1481. Min Act: -0.0002

Data Index: 336063 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1538. Min Act: -0.0002

Data Index: 117173 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1398. Min Act: -0.0002

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1441. Min Act: -0.0002

Data Index: 259938 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1336. Min Act: -0.0002

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1338. Min Act: -0.0002

Data Index: 1198585 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1280. Min Act: -0.0002

Data Index: 695869 (C4 (Web Text))

Max Activating Token Index: 83