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

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

Neuron 2411 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7095. Min Act: -0.0000

Data Index: 90969 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7272. Min Act: -0.0000

Data Index: 65629 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1304596 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1185634 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5762. Min Act: -0.0000

Data Index: 855166 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5652. Min Act: -0.0000

Data Index: 21142 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5484. Min Act: -0.0000

Data Index: 855182 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5017. Min Act: -0.0000

Data Index: 946127 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5320. Min Act: 0.0000

Data Index: 421112 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1238380 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4483. Min Act: -0.0000

Data Index: 333737 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5186. Min Act: -0.0000

Data Index: 383396 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4899. Min Act: -0.0000

Data Index: 499609 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4663. Min Act: -0.0000

Data Index: 73766 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4882. Min Act: -0.0000

Data Index: 891549 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4654. Min Act: -0.0000

Data Index: 667520 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1328514 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4685. Min Act: -0.0000

Data Index: 425774 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1188818 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4200. Min Act: -0.0000

Data Index: 860647 (C4 (Web Text))

Max Activating Token Index: 416