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

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

Neuron 5008 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: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0000

Data Index: 841796 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1256081 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0487. Min Act: -0.0000

Data Index: 339239 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0513. Min Act: -0.0000

Data Index: 588694 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1292097 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0569. Min Act: -0.0001

Data Index: 934187 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0472. Min Act: -0.0001

Data Index: 587725 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1080407 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0399. Min Act: -0.0000

Data Index: 111300 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1068740 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0410. Min Act: -0.0000

Data Index: 264298 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0455. Min Act: -0.0000

Data Index: 286632 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0415. Min Act: -0.0000

Data Index: 18594 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0425. Min Act: -0.0000

Data Index: 215165 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0448. Min Act: -0.0000

Data Index: 255880 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0451. Min Act: -0.0000

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1209225 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0438. Min Act: -0.0000

Data Index: 747537 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1044036 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1241110 (C4 (Web Text))

Max Activating Token Index: 372