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

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

Neuron 4582 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: 0.9336. Min Range: -0.9336

Max Act: 0.9301. Min Act: -0.0002

Data Index: 158897 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.9336. Min Act: -0.0002

Data Index: 338530 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8593. Min Act: -0.0002

Data Index: 407835 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8784. Min Act: -0.0002

Data Index: 228706 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8552. Min Act: -0.0002

Data Index: 535667 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8433. Min Act: -0.0002

Data Index: 129056 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8323. Min Act: -0.0002

Data Index: 651211 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8172. Min Act: -0.0002

Data Index: 250766 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8483. Min Act: -0.0002

Data Index: 323044 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8270. Min Act: -0.0002

Data Index: 142075 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8372. Min Act: -0.0002

Data Index: 1160147 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8210. Min Act: -0.0002

Data Index: 868524 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8250. Min Act: -0.0002

Data Index: 300627 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8197. Min Act: -0.0002

Data Index: 659503 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8169. Min Act: -0.0002

Data Index: 96538 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8238. Min Act: -0.0002

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8149. Min Act: -0.0002

Data Index: 25767 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8132. Min Act: -0.0002

Data Index: 623386 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8061. Min Act: -0.0002

Data Index: 502635 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8143. Min Act: -0.0002

Data Index: 1046515 (C4 (Web Text))

Max Activating Token Index: 144