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

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

Neuron 2804 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8420. Min Act: -0.0001

Data Index: 87362 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8657. Min Act: -0.0001

Data Index: 828177 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7677. Min Act: -0.0002

Data Index: 778145 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7893. Min Act: -0.0002

Data Index: 227189 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8583. Min Act: -0.0001

Data Index: 17701 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8132. Min Act: -0.0001

Data Index: 68564 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7841. Min Act: -0.0001

Data Index: 821362 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7426. Min Act: -0.0001

Data Index: 223026 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7773. Min Act: -0.0002

Data Index: 1097879 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7965. Min Act: -0.0002

Data Index: 103657 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1062622 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7271. Min Act: -0.0002

Data Index: 61873 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7512. Min Act: -0.0001

Data Index: 96940 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1218266 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7161. Min Act: -0.0001

Data Index: 109476 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1304872 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7473. Min Act: -0.0001

Data Index: 861660 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6936. Min Act: -0.0002

Data Index: 811804 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7000. Min Act: -0.0002

Data Index: 415149 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1213574 (C4 (Web Text))

Max Activating Token Index: 392