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

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

Neuron 4718 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.1436. Min Act: -0.0000

Data Index: 68818 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.1936. Min Act: -0.0000

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.0453. Min Act: -0.0000

Data Index: 271721 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.0149. Min Act: -0.0000

Data Index: 409444 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.0248. Min Act: -0.0000

Data Index: 965613 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.8369. Min Act: -0.0000

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 4.1936. Min Range: -4.1936

Max Act: 4.1763. Min Act: -0.0000

Data Index: 792833 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.6142. Min Act: -0.0000

Data Index: 1323776 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.7605. Min Act: -0.0000

Data Index: 1204067 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.8866. Min Act: -0.0000

Data Index: 320223 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.9154. Min Act: -0.0000

Data Index: 1323966 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.9104. Min Act: -0.0000

Data Index: 220294 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.5464. Min Act: -0.0000

Data Index: 942684 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.6755. Min Act: -0.0000

Data Index: 784040 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.6356. Min Act: -0.0000

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.7970. Min Act: -0.0000

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.4814. Min Act: -0.0000

Data Index: 1075028 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.5679. Min Act: -0.0000

Data Index: 423064 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.7499. Min Act: -0.0000

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 4.1936. Min Range: -4.1936

Max Act: 3.5647. Min Act: -0.0000

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 184