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

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

Neuron 4421 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: 4.5147. Min Range: -4.5147

Max Act: 4.4273. Min Act: -0.0000

Data Index: 1266193 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.5147. Min Act: -0.0000

Data Index: 239730 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.8266. Min Act: -0.0000

Data Index: 20789 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.9143. Min Act: -0.0000

Data Index: 211976 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.9284. Min Act: -0.0000

Data Index: 397639 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.0932. Min Act: -0.0000

Data Index: 1450184 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.0697. Min Act: -0.0000

Data Index: 1246174 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.7057. Min Act: -0.0000

Data Index: 102647 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.6173. Min Act: -0.0000

Data Index: 185 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.5937. Min Act: -0.0000

Data Index: 109729 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.6227. Min Act: -0.0000

Data Index: 671121 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.7331. Min Act: -0.0000

Data Index: 1354020 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.2963. Min Act: -0.0000

Data Index: 1372807 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.2626. Min Act: -0.0000

Data Index: 502094 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.3510. Min Act: -0.0000

Data Index: 175813 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.3446. Min Act: -0.0000

Data Index: 601932 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.2732. Min Act: -0.0000

Data Index: 974506 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.3400. Min Act: -0.0000

Data Index: 1257107 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.0700. Min Act: -0.0000

Data Index: 546240 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 4.5147. Min Range: -4.5147

Max Act: 3.4463. Min Act: -0.0000

Data Index: 889396 (C4 (Web Text))

Max Activating Token Index: 247