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

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

Neuron 80 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: 0.9529. Min Range: -0.9529

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1472559 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1378366 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1516336 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1376898 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1605077 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1438730 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1546105 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1644232 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1453996 (Python Code)

Max Activating Token Index: 332

Text #9

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1439613 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8316. Min Act: -0.0000

Data Index: 329807 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1607187 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1496581 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1656272 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1517463 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1616573 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1404964 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7181. Min Act: -0.0000

Data Index: 884715 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1360544 (Python Code)

Max Activating Token Index: 385

Text #19

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1567864 (Python Code)

Max Activating Token Index: 598