Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.5508. Min Act: -0.0000

Data Index: 329337 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.5342. Min Act: 0.0000

Data Index: 754312 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4929. Min Act: 0.0001

Data Index: 83746 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4943. Min Act: -0.0000

Data Index: 764044 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4785. Min Act: -0.0000

Data Index: 771939 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.5086. Min Act: 0.0001

Data Index: 898816 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4880. Min Act: 0.0001

Data Index: 510218 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4622. Min Act: 0.0000

Data Index: 665662 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4467. Min Act: -0.0000

Data Index: 759800 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4346. Min Act: -0.0000

Data Index: 232901 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4408. Min Act: -0.0000

Data Index: 250818 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4404. Min Act: -0.0000

Data Index: 206608 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1321661 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4296. Min Act: 0.0000

Data Index: 1075040 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4259. Min Act: -0.0000

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4322. Min Act: -0.0000

Data Index: 322515 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4147. Min Act: -0.0000

Data Index: 875568 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1087251 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1167198 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4035. Min Act: -0.0000

Data Index: 186730 (C4 (Web Text))

Max Activating Token Index: 777