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

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

Neuron 2814 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: 3.6802. Min Range: -3.6802

Max Act: 3.6802. Min Act: -0.0000

Data Index: 1081093 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.3389. Min Act: -0.0000

Data Index: 1220402 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.5607. Min Act: -0.0001

Data Index: 1012750 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.2806. Min Act: -0.0000

Data Index: 1050966 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.0510. Min Act: -0.0000

Data Index: 814719 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.1246. Min Act: -0.0000

Data Index: 344480 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8391. Min Act: -0.0000

Data Index: 1121097 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.9149. Min Act: -0.0000

Data Index: 1113585 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8971. Min Act: -0.0000

Data Index: 829827 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8757. Min Act: -0.0001

Data Index: 757163 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.7365. Min Act: -0.0000

Data Index: 475208 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8741. Min Act: -0.0000

Data Index: 882090 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8748. Min Act: -0.0000

Data Index: 761427 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.7276. Min Act: -0.0000

Data Index: 262776 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8183. Min Act: -0.0000

Data Index: 685368 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6702. Min Act: -0.0000

Data Index: 768759 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6643. Min Act: -0.0000

Data Index: 447576 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6067. Min Act: -0.0000

Data Index: 1107871 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.7183. Min Act: -0.0000

Data Index: 190712 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.7255. Min Act: -0.0001

Data Index: 1222198 (C4 (Web Text))

Max Activating Token Index: 8