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

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

Neuron 4978 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: 3.1313. Min Range: -3.1313

Max Act: 2.9601. Min Act: -0.0000

Data Index: 1022958 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.8394. Min Act: -0.0000

Data Index: 426371 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.7692. Min Act: -0.0000

Data Index: 862149 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.6851. Min Act: -0.0001

Data Index: 262205 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5444. Min Act: -0.0000

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.3161. Min Act: -0.0000

Data Index: 301336 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.3761. Min Act: -0.0000

Data Index: 1309993 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5650. Min Act: -0.0000

Data Index: 201191 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.4249. Min Act: -0.0000

Data Index: 994128 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5252. Min Act: -0.0000

Data Index: 1342016 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.1313. Min Range: -3.1313

Max Act: 3.1313. Min Act: -0.0000

Data Index: 1022003 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5780. Min Act: -0.0000

Data Index: 637401 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.4936. Min Act: -0.0000

Data Index: 996266 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5763. Min Act: -0.0001

Data Index: 531270 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.0889. Min Act: -0.0000

Data Index: 1042759 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5299. Min Act: -0.0000

Data Index: 856830 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.3230. Min Act: -0.0001

Data Index: 924524 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1019492 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.3750. Min Act: -0.0001

Data Index: 568686 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 3.1313. Min Range: -3.1313

Max Act: 2.1516. Min Act: -0.0000

Data Index: 3942 (C4 (Web Text))

Max Activating Token Index: 868