Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.4285. Min Act: -0.0000

Data Index: 321918 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3917. Min Act: -0.0000

Data Index: 804355 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3962. Min Act: -0.0001

Data Index: 188140 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1005479 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3536. Min Act: -0.0001

Data Index: 419513 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3715. Min Act: -0.0001

Data Index: 697589 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3698. Min Act: -0.0001

Data Index: 715165 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3798. Min Act: -0.0001

Data Index: 57250 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3649. Min Act: -0.0000

Data Index: 218239 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3632. Min Act: -0.0001

Data Index: 674810 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3594. Min Act: -0.0000

Data Index: 956862 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3437. Min Act: -0.0001

Data Index: 620864 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3805. Min Act: -0.0001

Data Index: 838709 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3531. Min Act: -0.0001

Data Index: 862228 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3459. Min Act: -0.0001

Data Index: 308631 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3554. Min Act: -0.0001

Data Index: 926254 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3301. Min Act: -0.0000

Data Index: 423569 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3287. Min Act: -0.0001

Data Index: 581834 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1079932 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3372. Min Act: -0.0000

Data Index: 997534 (C4 (Web Text))

Max Activating Token Index: 694