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

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

Neuron 291 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: 1.3487. Min Range: -1.3487

Max Act: 1.3487. Min Act: -0.0002

Data Index: 1154589 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.3020. Min Act: -0.0002

Data Index: 1217073 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2985. Min Act: -0.0002

Data Index: 894305 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.3209. Min Act: -0.0003

Data Index: 618868 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2662. Min Act: -0.0003

Data Index: 140200 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2853. Min Act: -0.0002

Data Index: 479920 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2412. Min Act: -0.0002

Data Index: 816140 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2571. Min Act: -0.0002

Data Index: 882428 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2439. Min Act: -0.0002

Data Index: 1049932 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2489. Min Act: -0.0002

Data Index: 380498 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2374. Min Act: -0.0002

Data Index: 50561 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2626. Min Act: -0.0002

Data Index: 661022 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2484. Min Act: -0.0002

Data Index: 969628 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2295. Min Act: -0.0002

Data Index: 1288323 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2338. Min Act: -0.0002

Data Index: 57931 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2269. Min Act: -0.0002

Data Index: 78534 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2117. Min Act: -0.0002

Data Index: 463977 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2236. Min Act: -0.0002

Data Index: 1269460 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2392. Min Act: -0.0002

Data Index: 1120536 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.1905. Min Act: -0.0002

Data Index: 1321173 (C4 (Web Text))

Max Activating Token Index: 175