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

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

Neuron 4500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0885. Min Range: -3.0885

Max Act: 3.0885. Min Act: -0.0000

Data Index: 716696 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 3.0885. Min Range: -3.0885

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1277143 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.8520. Min Act: -0.0000

Data Index: 983258 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.7291. Min Act: -0.0000

Data Index: 121418 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1313475 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.5872. Min Act: -0.0000

Data Index: 428049 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.5715. Min Act: -0.0000

Data Index: 1244668 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.5457. Min Act: -0.0000

Data Index: 455255 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.5211. Min Act: -0.0000

Data Index: 61409 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4939. Min Act: -0.0000

Data Index: 275113 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4837. Min Act: -0.0000

Data Index: 1060344 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.5505. Min Act: -0.0000

Data Index: 749952 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4330. Min Act: -0.0000

Data Index: 943140 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4374. Min Act: -0.0000

Data Index: 276697 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4274. Min Act: -0.0000

Data Index: 1250959 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4044. Min Act: -0.0000

Data Index: 312388 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1145535 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.4254. Min Act: -0.0000

Data Index: 57342 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.3173. Min Act: -0.0000

Data Index: 741003 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 3.0885. Min Range: -3.0885

Max Act: 1.3938. Min Act: -0.0000

Data Index: 342196 (C4 (Web Text))

Max Activating Token Index: 413