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

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

Neuron 278 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7867. Min Act: -0.0000

Data Index: 90192 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1543285 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1554125 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1495442 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1459671 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1612092 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6119. Min Act: -0.0000

Data Index: 250642 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1144551 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5781. Min Act: -0.0000

Data Index: 159467 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1513223 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6045. Min Act: -0.0000

Data Index: 700939 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1189753 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1524980 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5622. Min Act: -0.0000

Data Index: 529335 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5778. Min Act: -0.0000

Data Index: 809982 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1427752 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5471. Min Act: -0.0000

Data Index: 602455 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5954. Min Act: -0.0000

Data Index: 442091 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5776. Min Act: -0.0000

Data Index: 418908 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1379574 (Python Code)

Max Activating Token Index: 721