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

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

Neuron 1500 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: 2.0510. Min Range: -2.0510

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1248545 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.0510. Min Range: -2.0510

Max Act: 2.0076. Min Act: -0.0000

Data Index: 491562 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.9339. Min Act: -0.0000

Data Index: 407490 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.9997. Min Act: -0.0000

Data Index: 677131 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.0510. Min Range: -2.0510

Max Act: 2.0330. Min Act: -0.0000

Data Index: 778265 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.8219. Min Act: -0.0000

Data Index: 14161 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.8522. Min Act: -0.0000

Data Index: 775487 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.7133. Min Act: -0.0000

Data Index: 159418 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.9192. Min Act: -0.0000

Data Index: 644758 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.7869. Min Act: -0.0000

Data Index: 519424 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.7672. Min Act: -0.0000

Data Index: 639482 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1249305 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.8579. Min Act: -0.0000

Data Index: 343840 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1082731 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.5301. Min Act: -0.0000

Data Index: 277746 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.8233. Min Act: -0.0000

Data Index: 818318 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.6064. Min Act: -0.0000

Data Index: 981284 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1178667 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.5579. Min Act: -0.0000

Data Index: 1053777 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 2.0510. Min Range: -2.0510

Max Act: 1.5476. Min Act: -0.0000

Data Index: 753943 (C4 (Web Text))

Max Activating Token Index: 485