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

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

Neuron 5455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0148. Min Range: -3.0148

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1127840 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.3436. Min Act: -0.0000

Data Index: 359282 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4509. Min Act: -0.0000

Data Index: 958385 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4764. Min Act: -0.0000

Data Index: 675109 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.3624. Min Act: -0.0000

Data Index: 581789 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4199. Min Act: -0.0000

Data Index: 1185775 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.1279. Min Act: -0.0000

Data Index: 371065 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1310802 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4447. Min Act: -0.0001

Data Index: 208601 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.0565. Min Act: -0.0000

Data Index: 937026 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8990. Min Act: -0.0000

Data Index: 1277018 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.9686. Min Act: -0.0000

Data Index: 934392 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.9882. Min Act: -0.0000

Data Index: 198549 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8925. Min Act: -0.0000

Data Index: 295052 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8480. Min Act: -0.0000

Data Index: 1051358 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.7294. Min Act: -0.0000

Data Index: 567585 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8836. Min Act: -0.0000

Data Index: 49526 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8681. Min Act: -0.0001

Data Index: 374598 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8734. Min Act: -0.0000

Data Index: 299591 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.8842. Min Act: -0.0000

Data Index: 851613 (C4 (Web Text))

Max Activating Token Index: 465