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

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

Neuron 3432 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: 1.4284. Min Range: -1.4284

Max Act: 1.4284. Min Act: -0.0002

Data Index: 794312 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.3905. Min Act: -0.0002

Data Index: 1353617 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.3354. Min Act: -0.0002

Data Index: 418714 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2505. Min Act: -0.0002

Data Index: 736365 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2325. Min Act: -0.0002

Data Index: 526979 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1850. Min Act: -0.0002

Data Index: 491185 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1874. Min Act: -0.0002

Data Index: 1049576 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1515. Min Act: -0.0002

Data Index: 975208 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1176. Min Act: -0.0002

Data Index: 895727 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1567. Min Act: -0.0002

Data Index: 1217716 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1502. Min Act: -0.0002

Data Index: 144908 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1340. Min Act: -0.0002

Data Index: 222205 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1418. Min Act: -0.0002

Data Index: 1284095 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1219. Min Act: -0.0002

Data Index: 457802 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1303. Min Act: -0.0002

Data Index: 756086 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1039. Min Act: -0.0002

Data Index: 243741 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0957. Min Act: -0.0002

Data Index: 1074336 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1001. Min Act: -0.0003

Data Index: 276765 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1111. Min Act: -0.0002

Data Index: 281943 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0876. Min Act: -0.0002

Data Index: 308391 (C4 (Web Text))

Max Activating Token Index: 806