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

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

Neuron 2279 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: 5.5677. Min Range: -5.5677

Max Act: 5.5677. Min Act: -0.0000

Data Index: 909011 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 5.5677. Min Range: -5.5677

Max Act: 5.3434. Min Act: -0.0000

Data Index: 621364 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 5.5677. Min Range: -5.5677

Max Act: 5.2856. Min Act: -0.0000

Data Index: 189473 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 5.5677. Min Range: -5.5677

Max Act: 5.5494. Min Act: -0.0000

Data Index: 183010 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 5.5677. Min Range: -5.5677

Max Act: 5.0696. Min Act: -0.0000

Data Index: 1318008 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.9326. Min Act: -0.0000

Data Index: 876161 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.9315. Min Act: -0.0000

Data Index: 1533250 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.8095. Min Act: -0.0000

Data Index: 1084806 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.7652. Min Act: -0.0000

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.7442. Min Act: -0.0000

Data Index: 834509 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 5.5677. Min Range: -5.5677

Max Act: 5.0467. Min Act: -0.0000

Data Index: 1212948 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.8070. Min Act: -0.0000

Data Index: 1140063 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.2497. Min Act: -0.0000

Data Index: 1287454 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.5641. Min Act: -0.0000

Data Index: 210438 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.4038. Min Act: -0.0000

Data Index: 594357 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.3311. Min Act: -0.0000

Data Index: 1479064 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.5001. Min Act: -0.0000

Data Index: 1382778 (Python Code)

Max Activating Token Index: 601

Text #17

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.3266. Min Act: -0.0000

Data Index: 1287474 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.4961. Min Act: -0.0000

Data Index: 361082 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 5.5677. Min Range: -5.5677

Max Act: 4.1180. Min Act: -0.0000

Data Index: 1338099 (C4 (Web Text))

Max Activating Token Index: 753