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

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

Neuron 5916 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1276. Min Range: -7.1276

Max Act: 6.6628. Min Act: -0.0000

Data Index: 1412862 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 7.1276. Min Range: -7.1276

Max Act: 7.1276. Min Act: -0.0000

Data Index: 1526630 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 7.1276. Min Range: -7.1276

Max Act: 6.9518. Min Act: -0.0000

Data Index: 1454993 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.9884. Min Act: -0.0000

Data Index: 1612384 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.5771. Min Act: -0.0000

Data Index: 1390063 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.9303. Min Act: -0.0000

Data Index: 1409570 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.7238. Min Act: -0.0000

Data Index: 1364645 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.8835. Min Act: -0.0000

Data Index: 1517296 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.6749. Min Act: -0.0000

Data Index: 1370309 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.9881. Min Act: -0.0000

Data Index: 1578872 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.3356. Min Act: -0.0000

Data Index: 1428152 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.7135. Min Act: -0.0000

Data Index: 1362838 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.3185. Min Act: -0.0000

Data Index: 1532697 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.6430. Min Act: -0.0000

Data Index: 1545613 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.2707. Min Act: -0.0000

Data Index: 1459936 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.2319. Min Act: -0.0000

Data Index: 1653816 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.5795. Min Act: -0.0000

Data Index: 1480910 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.5360. Min Act: -0.0000

Data Index: 1374316 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.4983. Min Act: -0.0000

Data Index: 1614165 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 7.1276. Min Range: -7.1276

Max Act: 5.0651. Min Act: -0.0000

Data Index: 1428046 (Python Code)

Max Activating Token Index: 686