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

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

Neuron 1052 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: 2.3270. Min Range: -2.3270

Max Act: 2.3270. Min Act: -0.0000

Data Index: 620610 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 2.3270. Min Range: -2.3270

Max Act: 2.1045. Min Act: -0.0000

Data Index: 1059994 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 2.3270. Min Range: -2.3270

Max Act: 2.1761. Min Act: -0.0000

Data Index: 592587 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1505898 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1458806 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.9467. Min Act: -0.0000

Data Index: 1540309 (Python Code)

Max Activating Token Index: 672

Text #6

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1654062 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7120. Min Act: -0.0000

Data Index: 762255 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1648350 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1370275 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1446236 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1531939 (Python Code)

Max Activating Token Index: 486

Text #12

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1197885 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1605929 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1219555 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7702. Min Act: -0.0000

Data Index: 1573920 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7675. Min Act: -0.0000

Data Index: 965701 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.6265. Min Act: -0.0000

Data Index: 1565587 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7272. Min Act: -0.0000

Data Index: 1468949 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 2.3270. Min Range: -2.3270

Max Act: 1.7123. Min Act: -0.0000

Data Index: 62877 (C4 (Web Text))

Max Activating Token Index: 881