Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 324 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0003

Data Index: 928187 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0576. Min Act: -0.0003

Data Index: 665040 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0566. Min Act: -0.0002

Data Index: 685843 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0555. Min Act: -0.0003

Data Index: 926843 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0577. Min Act: -0.0004

Data Index: 1244923 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0563. Min Act: -0.0003

Data Index: 158844 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1280313 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1197763 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0542. Min Act: -0.0003

Data Index: 988396 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0543. Min Act: -0.0003

Data Index: 522061 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1346251 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1085295 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0518. Min Act: -0.0002

Data Index: 235160 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0507. Min Act: -0.0003

Data Index: 167318 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0522. Min Act: -0.0002

Data Index: 582206 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0520. Min Act: -0.0004

Data Index: 1196941 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0518. Min Act: -0.0003

Data Index: 604898 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0519. Min Act: -0.0002

Data Index: 596930 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1290785 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0506. Min Act: -0.0003

Data Index: 956836 (C4 (Web Text))

Max Activating Token Index: 563