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

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

Neuron 5513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7703. Min Act: -0.0000

Data Index: 780262 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1137707 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6800. Min Act: 0.0000

Data Index: 388822 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1254279 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1036425 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5300. Min Act: -0.0000

Data Index: 694408 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4991. Min Act: -0.0000

Data Index: 152520 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5211. Min Act: 0.0001

Data Index: 391242 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5334. Min Act: -0.0000

Data Index: 308666 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4920. Min Act: 0.0001

Data Index: 225905 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4684. Min Act: 0.0000

Data Index: 1136266 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4860. Min Act: -0.0000

Data Index: 631127 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4571. Min Act: -0.0000

Data Index: 179144 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4323. Min Act: -0.0000

Data Index: 650099 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4485. Min Act: -0.0000

Data Index: 509302 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4570. Min Act: -0.0000

Data Index: 765725 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4381. Min Act: 0.0000

Data Index: 1044495 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4312. Min Act: -0.0000

Data Index: 621561 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1045063 (C4 (Web Text))

Max Activating Token Index: 164