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

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

Neuron 4454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9314. Min Range: -3.9314

Max Act: 3.9314. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.9314. Min Range: -3.9314

Max Act: 3.4333. Min Act: -0.0000

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.9314. Min Range: -3.9314

Max Act: 3.0783. Min Act: -0.0000

Data Index: 1029044 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.4904. Min Act: -0.0000

Data Index: 707914 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.4401. Min Act: -0.0000

Data Index: 165990 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.6377. Min Act: -0.0000

Data Index: 543659 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.6024. Min Act: -0.0000

Data Index: 937555 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3437. Min Act: -0.0000

Data Index: 181336 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3260. Min Act: -0.0000

Data Index: 854302 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3962. Min Act: -0.0000

Data Index: 246671 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3708. Min Act: -0.0000

Data Index: 923534 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1095133 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.4427. Min Act: -0.0000

Data Index: 419290 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3126. Min Act: -0.0000

Data Index: 753492 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.3920. Min Act: -0.0000

Data Index: 249607 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.2494. Min Act: -0.0000

Data Index: 630904 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.1337. Min Act: -0.0000

Data Index: 755524 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.2952. Min Act: -0.0000

Data Index: 573659 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 3.9314. Min Range: -3.9314

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 3.9314. Min Range: -3.9314

Max Act: 2.0233. Min Act: -0.0000

Data Index: 1197869 (C4 (Web Text))

Max Activating Token Index: 350