Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4858. Min Act: -0.0000

Data Index: 642694 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4628. Min Act: -0.0000

Data Index: 695156 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1343909 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1191797 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4596. Min Act: -0.0000

Data Index: 199925 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1637990 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4032. Min Act: -0.0000

Data Index: 101544 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3866. Min Act: -0.0000

Data Index: 607414 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4078. Min Act: -0.0000

Data Index: 456020 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3894. Min Act: -0.0000

Data Index: 404591 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1086962 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4341. Min Act: -0.0000

Data Index: 891791 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4155. Min Act: -0.0000

Data Index: 728577 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1600486 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4203. Min Act: -0.0000

Data Index: 473488 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4192. Min Act: -0.0000

Data Index: 621856 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3875. Min Act: -0.0000

Data Index: 347819 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3887. Min Act: -0.0000

Data Index: 825929 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.3674. Min Act: -0.0000

Data Index: 997124 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.4858. Min Range: -0.4858

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1324483 (C4 (Web Text))

Max Activating Token Index: 265