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

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

Neuron 4711 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3105. Min Act: -0.0001

Data Index: 902070 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3083. Min Act: -0.0001

Data Index: 1425452 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2846. Min Act: -0.0000

Data Index: 818311 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1163244 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2656. Min Act: -0.0000

Data Index: 503830 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2690. Min Act: -0.0001

Data Index: 1487980 (Python Code)

Max Activating Token Index: 557

Text #6

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1870. Min Act: -0.0000

Data Index: 813644 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1378797 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3317. Min Act: -0.0001

Data Index: 741828 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1643. Min Act: -0.0000

Data Index: 801138 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1963. Min Act: -0.0001

Data Index: 52307 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2144. Min Act: -0.0001

Data Index: 1176626 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1088034 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1387. Min Act: -0.0001

Data Index: 778106 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1890. Min Act: -0.0001

Data Index: 738022 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1105622 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1245. Min Act: -0.0001

Data Index: 36541 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1068046 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1158461 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0807. Min Act: -0.0001

Data Index: 316188 (C4 (Web Text))

Max Activating Token Index: 727