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

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

Neuron 4729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.3250. Min Act: -0.0000

Data Index: 1184112 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.3649. Min Act: -0.0000

Data Index: 272363 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0420. Min Act: -0.0000

Data Index: 73401 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0389. Min Act: -0.0000

Data Index: 692050 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 1.3649. Min Range: -1.3649

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1269124 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1346042 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8591. Min Act: -0.0000

Data Index: 473087 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8327. Min Act: -0.0000

Data Index: 228518 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8250. Min Act: -0.0000

Data Index: 417761 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.8189. Min Act: -0.0000

Data Index: 299817 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1004309 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.7671. Min Act: -0.0000

Data Index: 558146 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.7416. Min Act: -0.0000

Data Index: 619838 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6910. Min Act: -0.0000

Data Index: 44516 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6896. Min Act: -0.0000

Data Index: 116866 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1200772 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.7519. Min Act: -0.0000

Data Index: 246293 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6786. Min Act: -0.0000

Data Index: 27144 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1049947 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.3649. Min Range: -1.3649

Max Act: 0.6182. Min Act: -0.0000

Data Index: 291651 (C4 (Web Text))

Max Activating Token Index: 840