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

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

Neuron 3416 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: 6.1340. Min Range: -6.1340

Max Act: 6.1340. Min Act: -0.0000

Data Index: 228964 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 6.1340. Min Range: -6.1340

Max Act: 6.0577. Min Act: -0.0000

Data Index: 1088268 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.9747. Min Act: -0.0000

Data Index: 49590 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.5737. Min Act: -0.0000

Data Index: 188651 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.5846. Min Act: -0.0000

Data Index: 1054439 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.5696. Min Act: -0.0000

Data Index: 54392 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.4513. Min Act: -0.0000

Data Index: 525630 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.4842. Min Act: -0.0000

Data Index: 245910 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.3115. Min Act: -0.0000

Data Index: 954928 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.3073. Min Act: -0.0000

Data Index: 1028472 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.3465. Min Act: -0.0000

Data Index: 137276 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.3442. Min Act: -0.0000

Data Index: 524460 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.3502. Min Act: -0.0000

Data Index: 365457 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.2963. Min Act: -0.0000

Data Index: 487058 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.4653. Min Act: -0.0000

Data Index: 411867 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.2364. Min Act: -0.0000

Data Index: 968062 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 6.1340. Min Range: -6.1340

Max Act: 4.9370. Min Act: -0.0000

Data Index: 974171 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.2317. Min Act: -0.0000

Data Index: 1302130 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 6.1340. Min Range: -6.1340

Max Act: 4.9699. Min Act: -0.0000

Data Index: 163008 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 6.1340. Min Range: -6.1340

Max Act: 5.1595. Min Act: -0.0000

Data Index: 1148841 (C4 (Web Text))

Max Activating Token Index: 989