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

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

Neuron 5991 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2372. Min Range: -4.2372

Max Act: 4.2372. Min Act: -0.0000

Data Index: 1129970 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.5142. Min Act: -0.0000

Data Index: 1061152 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.4896. Min Act: -0.0000

Data Index: 489507 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.1094. Min Act: -0.0000

Data Index: 690874 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.4440. Min Act: -0.0000

Data Index: 541204 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.3153. Min Act: -0.0000

Data Index: 1232773 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.4776. Min Act: -0.0000

Data Index: 850664 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.4462. Min Act: -0.0000

Data Index: 193572 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.1353. Min Act: -0.0000

Data Index: 204537 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.0896. Min Act: -0.0000

Data Index: 650126 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.5679. Min Act: -0.0000

Data Index: 348641 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.1015. Min Act: -0.0000

Data Index: 48721 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 4.2372. Min Range: -4.2372

Max Act: 2.9660. Min Act: -0.0000

Data Index: 897988 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.0936. Min Act: -0.0000

Data Index: 907569 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 4.2372. Min Range: -4.2372

Max Act: 2.9356. Min Act: -0.0000

Data Index: 1316871 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 4.2372. Min Range: -4.2372

Max Act: 2.7904. Min Act: -0.0000

Data Index: 1072325 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 4.2372. Min Range: -4.2372

Max Act: 2.9106. Min Act: -0.0000

Data Index: 486133 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.0463. Min Act: -0.0000

Data Index: 97594 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 4.2372. Min Range: -4.2372

Max Act: 2.6316. Min Act: -0.0000

Data Index: 271262 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 4.2372. Min Range: -4.2372

Max Act: 3.0420. Min Act: -0.0000

Data Index: 128540 (C4 (Web Text))

Max Activating Token Index: 796