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

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

Neuron 4026 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: 1.2681. Min Range: -1.2681

Max Act: 1.2681. Min Act: -0.0000

Data Index: 437207 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0047. Min Act: -0.0000

Data Index: 918531 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1105736 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0226. Min Act: -0.0000

Data Index: 525866 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0218. Min Act: -0.0000

Data Index: 841074 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1210713 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9990. Min Act: -0.0000

Data Index: 946334 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1046187 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1323976 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9431. Min Act: -0.0000

Data Index: 115919 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1358989 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8350. Min Act: -0.0000

Data Index: 128917 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8661. Min Act: -0.0000

Data Index: 758046 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9161. Min Act: -0.0000

Data Index: 774187 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8550. Min Act: -0.0000

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1218638 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8299. Min Act: -0.0000

Data Index: 623846 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8261. Min Act: -0.0000

Data Index: 114765 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8143. Min Act: -0.0000

Data Index: 145094 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8090. Min Act: -0.0000

Data Index: 725059 (C4 (Web Text))

Max Activating Token Index: 492