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

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

Neuron 4959 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: 1.8521. Min Range: -1.8521

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1046677 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1065799 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.4981. Min Act: -0.0000

Data Index: 742026 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.3472. Min Act: -0.0000

Data Index: 558832 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1334599 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.3264. Min Act: -0.0000

Data Index: 874265 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.3833. Min Act: -0.0000

Data Index: 96594 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.3167. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2703. Min Act: -0.0000

Data Index: 926411 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2488. Min Act: -0.0000

Data Index: 995991 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2528. Min Act: -0.0000

Data Index: 392128 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2142. Min Act: -0.0000

Data Index: 532131 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1209488 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.1931. Min Act: -0.0000

Data Index: 195602 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2395. Min Act: -0.0000

Data Index: 772555 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1301115 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.1460. Min Act: -0.0000

Data Index: 85972 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.1831. Min Act: -0.0000

Data Index: 575282 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1036238 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.8521. Min Range: -1.8521

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1070197 (C4 (Web Text))

Max Activating Token Index: 138