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

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

Neuron 3866 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: 1.0560. Min Range: -1.0560

Max Act: 1.0560. Min Act: -0.0001

Data Index: 500658 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1196435 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1226523 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9618. Min Act: -0.0001

Data Index: 1165053 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0043. Min Act: -0.0001

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9695. Min Act: -0.0000

Data Index: 557448 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9282. Min Act: -0.0001

Data Index: 7003 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.7672. Min Act: -0.0000

Data Index: 616662 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8639. Min Act: -0.0000

Data Index: 815367 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1220361 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1026286 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1025790 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9585. Min Act: -0.0000

Data Index: 95866 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.6863. Min Act: -0.0001

Data Index: 895644 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1010948 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.5891. Min Act: -0.0000

Data Index: 614058 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8388. Min Act: -0.0000

Data Index: 338556 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.7729. Min Act: -0.0000

Data Index: 621210 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1143654 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.7365. Min Act: -0.0000

Data Index: 792620 (C4 (Web Text))

Max Activating Token Index: 525