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

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

Neuron 5593 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: 1.3129. Min Range: -1.3129

Max Act: 1.3129. Min Act: -0.0000

Data Index: 383738 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1119348 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.2546. Min Act: -0.0000

Data Index: 346289 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.2222. Min Act: -0.0000

Data Index: 112972 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1326903 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.2004. Min Act: -0.0000

Data Index: 144469 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0623. Min Act: -0.0000

Data Index: 363196 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0831. Min Act: -0.0000

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0733. Min Act: -0.0000

Data Index: 335954 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0772. Min Act: -0.0000

Data Index: 93408 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0932. Min Act: -0.0000

Data Index: 532083 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0087. Min Act: -0.0000

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9792. Min Act: -0.0000

Data Index: 281556 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0393. Min Act: -0.0000

Data Index: 662119 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1319260 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0845. Min Act: -0.0000

Data Index: 604793 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9529. Min Act: -0.0000

Data Index: 415362 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0273. Min Act: -0.0000

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1601407 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9436. Min Act: -0.0000

Data Index: 156696 (C4 (Web Text))

Max Activating Token Index: 459