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

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

Neuron 2240 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: 2.5423. Min Range: -2.5423

Max Act: 2.5423. Min Act: -0.0000

Data Index: 1172329 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1068533 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.2546. Min Act: -0.0000

Data Index: 1240522 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.1329. Min Act: -0.0000

Data Index: 879350 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.0672. Min Act: -0.0000

Data Index: 264833 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1103765 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9222. Min Act: -0.0000

Data Index: 5957 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 2.5423. Min Range: -2.5423

Max Act: 2.0185. Min Act: -0.0000

Data Index: 1037608 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8902. Min Act: -0.0000

Data Index: 992462 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9626. Min Act: -0.0000

Data Index: 122572 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9369. Min Act: -0.0000

Data Index: 733106 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8188. Min Act: -0.0000

Data Index: 110607 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9219. Min Act: -0.0001

Data Index: 579257 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.7390. Min Act: -0.0000

Data Index: 156939 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9367. Min Act: -0.0000

Data Index: 1350067 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1204368 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8294. Min Act: -0.0000

Data Index: 454583 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.9382. Min Act: -0.0000

Data Index: 1213451 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8102. Min Act: -0.0000

Data Index: 957187 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 2.5423. Min Range: -2.5423

Max Act: 1.8822. Min Act: -0.0000

Data Index: 380239 (C4 (Web Text))

Max Activating Token Index: 161