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

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

Neuron 1445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1166818 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.7056. Min Act: -0.0001

Data Index: 790143 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.7049. Min Act: -0.0001

Data Index: 640505 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6635. Min Act: -0.0001

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6617. Min Act: -0.0001

Data Index: 938244 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1214931 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5723. Min Act: -0.0001

Data Index: 789534 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5925. Min Act: -0.0001

Data Index: 761271 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6026. Min Act: -0.0001

Data Index: 873514 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1216354 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5664. Min Act: -0.0001

Data Index: 89883 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5870. Min Act: -0.0001

Data Index: 189199 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5864. Min Act: -0.0001

Data Index: 1067217 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5951. Min Act: -0.0001

Data Index: 987743 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5640. Min Act: -0.0001

Data Index: 488025 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5391. Min Act: -0.0001

Data Index: 601558 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1244511 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5383. Min Act: -0.0001

Data Index: 620724 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5628. Min Act: -0.0001

Data Index: 771051 (C4 (Web Text))

Max Activating Token Index: 315