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

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

Neuron 3559 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: 0.6781. Min Range: -0.6781

Max Act: 0.6634. Min Act: -0.0002

Data Index: 1081298 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6777. Min Act: -0.0002

Data Index: 357381 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6781. Min Act: -0.0002

Data Index: 572352 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6406. Min Act: -0.0002

Data Index: 860181 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6237. Min Act: -0.0002

Data Index: 265665 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6137. Min Act: -0.0002

Data Index: 325192 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6279. Min Act: -0.0002

Data Index: 730434 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6174. Min Act: -0.0002

Data Index: 1224859 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6328. Min Act: -0.0002

Data Index: 684964 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6225. Min Act: -0.0002

Data Index: 1352979 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6202. Min Act: -0.0002

Data Index: 719870 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6098. Min Act: -0.0002

Data Index: 26580 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6207. Min Act: -0.0002

Data Index: 579951 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6133. Min Act: -0.0002

Data Index: 1152298 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6044. Min Act: -0.0002

Data Index: 1147022 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6061. Min Act: -0.0002

Data Index: 1297092 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6049. Min Act: -0.0002

Data Index: 24112 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6005. Min Act: -0.0002

Data Index: 1324291 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6024. Min Act: -0.0002

Data Index: 1029613 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5973. Min Act: -0.0002

Data Index: 706947 (C4 (Web Text))

Max Activating Token Index: 343