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

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

Neuron 2390 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: 0.3466. Min Range: -0.3466

Max Act: 0.3466. Min Act: -0.0002

Data Index: 101228 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3390. Min Act: -0.0002

Data Index: 303792 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3358. Min Act: -0.0002

Data Index: 201414 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3351. Min Act: -0.0002

Data Index: 671753 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3289. Min Act: -0.0002

Data Index: 870531 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3188. Min Act: -0.0002

Data Index: 17558 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3149. Min Act: -0.0002

Data Index: 132292 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3214. Min Act: -0.0002

Data Index: 93439 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3207. Min Act: -0.0002

Data Index: 894428 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3155. Min Act: -0.0003

Data Index: 85491 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3140. Min Act: -0.0002

Data Index: 1316850 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3115. Min Act: -0.0002

Data Index: 260032 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3121. Min Act: -0.0003

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3141. Min Act: -0.0002

Data Index: 1187430 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3154. Min Act: -0.0002

Data Index: 294745 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3068. Min Act: -0.0002

Data Index: 240987 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3044. Min Act: -0.0002

Data Index: 1309390 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3121. Min Act: -0.0002

Data Index: 68868 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3048. Min Act: -0.0002

Data Index: 489456 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2988. Min Act: -0.0002

Data Index: 666910 (C4 (Web Text))

Max Activating Token Index: 74