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

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

Neuron 3672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.6431. Min Act: -0.0000

Data Index: 1635473 (Python Code)

Max Activating Token Index: 750

Text #1

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.4518. Min Act: -0.0000

Data Index: 1584972 (Python Code)

Max Activating Token Index: 672

Text #2

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.2652. Min Act: -0.0000

Data Index: 1546591 (Python Code)

Max Activating Token Index: 768

Text #3

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.2116. Min Act: -0.0000

Data Index: 1563419 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.3698. Min Act: -0.0000

Data Index: 1388081 (Python Code)

Max Activating Token Index: 293

Text #5

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.1745. Min Act: -0.0000

Data Index: 1514028 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.3388. Min Act: -0.0000

Data Index: 1450527 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.9947. Min Act: -0.0000

Data Index: 1493768 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.8225. Min Act: -0.0000

Data Index: 1519703 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 5.6431. Min Range: -5.6431

Max Act: 5.0160. Min Act: -0.0000

Data Index: 1373200 (Python Code)

Max Activating Token Index: 280

Text #10

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.6491. Min Act: -0.0000

Data Index: 1652529 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.4598. Min Act: -0.0000

Data Index: 1379977 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.4319. Min Act: -0.0000

Data Index: 1648083 (Python Code)

Max Activating Token Index: 841

Text #13

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.6166. Min Act: -0.0000

Data Index: 1444006 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.4968. Min Act: -0.0000

Data Index: 1503153 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.2297. Min Act: -0.0000

Data Index: 1640373 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.6057. Min Act: -0.0000

Data Index: 1533160 (Python Code)

Max Activating Token Index: 767

Text #17

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.3199. Min Act: -0.0000

Data Index: 1630958 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 5.6431. Min Range: -5.6431

Max Act: 3.9718. Min Act: -0.0000

Data Index: 1537291 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 5.6431. Min Range: -5.6431

Max Act: 4.1432. Min Act: -0.0000

Data Index: 1531152 (Python Code)

Max Activating Token Index: 227