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

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

Neuron 4221 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1326276 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.4213. Min Act: 0.0001

Data Index: 922418 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.4395. Min Act: -0.0000

Data Index: 428065 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.4010. Min Act: -0.0000

Data Index: 989604 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3923. Min Act: -0.0000

Data Index: 215596 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3489. Min Act: -0.0000

Data Index: 4772 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3903. Min Act: -0.0000

Data Index: 383586 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3762. Min Act: -0.0000

Data Index: 428506 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3316. Min Act: -0.0000

Data Index: 583072 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3860. Min Act: -0.0000

Data Index: 965762 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3634. Min Act: -0.0000

Data Index: 7304 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3194. Min Act: -0.0000

Data Index: 273167 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3791. Min Act: -0.0000

Data Index: 960096 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3682. Min Act: -0.0000

Data Index: 344509 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3291. Min Act: -0.0000

Data Index: 329004 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3354. Min Act: -0.0000

Data Index: 806688 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3336. Min Act: -0.0000

Data Index: 801099 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3411. Min Act: 0.0000

Data Index: 1070486 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3450. Min Act: -0.0000

Data Index: 493924 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1480701 (Python Code)

Max Activating Token Index: 141