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

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

Neuron 4133 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2228. Min Range: -4.2228

Max Act: 4.2228. Min Act: 0.0000

Data Index: 949874 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 4.2228. Min Range: -4.2228

Max Act: 3.6239. Min Act: 0.0000

Data Index: 862493 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.9493. Min Act: -0.0000

Data Index: 123467 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.9457. Min Act: -0.0000

Data Index: 635200 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.5884. Min Act: 0.0000

Data Index: 541839 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.8508. Min Act: -0.0000

Data Index: 351503 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.5432. Min Act: -0.0000

Data Index: 927615 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.5424. Min Act: -0.0000

Data Index: 915104 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.7112. Min Act: -0.0000

Data Index: 814824 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.4668. Min Act: -0.0000

Data Index: 1259980 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.3017. Min Act: -0.0000

Data Index: 1324098 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.2816. Min Act: -0.0000

Data Index: 760588 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.2682. Min Act: -0.0000

Data Index: 180108 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.1334. Min Act: -0.0000

Data Index: 992331 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.2226. Min Act: -0.0000

Data Index: 810523 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.2108. Min Act: 0.0000

Data Index: 81083 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.2273. Min Act: -0.0000

Data Index: 660813 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.1956. Min Act: -0.0000

Data Index: 205978 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.1950. Min Act: 0.0000

Data Index: 646227 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 4.2228. Min Range: -4.2228

Max Act: 2.1523. Min Act: -0.0000

Data Index: 778839 (C4 (Web Text))

Max Activating Token Index: 174