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

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

Neuron 1918 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: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0000

Data Index: 64173 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4793. Min Act: -0.0000

Data Index: 470184 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4918. Min Act: -0.0000

Data Index: 397757 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4502. Min Act: -0.0000

Data Index: 964292 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1232675 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1053265 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4301. Min Act: -0.0000

Data Index: 254381 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4275. Min Act: -0.0000

Data Index: 573597 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4168. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1291921 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4355. Min Act: -0.0000

Data Index: 894562 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4122. Min Act: -0.0000

Data Index: 298566 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4015. Min Act: -0.0000

Data Index: 910771 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1019764 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3704. Min Act: -0.0000

Data Index: 542313 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1171135 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3593. Min Act: -0.0000

Data Index: 727352 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3867. Min Act: -0.0000

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3612. Min Act: -0.0000

Data Index: 383624 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.3541. Min Act: -0.0000

Data Index: 690339 (C4 (Web Text))

Max Activating Token Index: 944