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

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

Neuron 4183 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.6912. Min Act: -0.0002

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 4.3431. Min Range: -4.3431

Max Act: 4.3431. Min Act: -0.0002

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.6030. Min Act: -0.0002

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8605. Min Act: -0.0002

Data Index: 1243769 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8700. Min Act: -0.0002

Data Index: 1046127 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.7650. Min Act: -0.0002

Data Index: 274528 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.7706. Min Act: -0.0002

Data Index: 158570 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8330. Min Act: -0.0002

Data Index: 48638 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.7130. Min Act: -0.0002

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8800. Min Act: -0.0002

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.7145. Min Act: -0.0002

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.6520. Min Act: -0.0002

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8880. Min Act: -0.0002

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.7353. Min Act: -0.0002

Data Index: 576186 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.6068. Min Act: -0.0002

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.3669. Min Act: -0.0002

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8553. Min Act: -0.0002

Data Index: 1270561 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.3879. Min Act: -0.0002

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.8669. Min Act: -0.0002

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 4.3431. Min Range: -4.3431

Max Act: 3.6965. Min Act: -0.0002

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 634