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

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

Neuron 4007 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: 0.5788. Min Range: -0.5788

Max Act: 0.5788. Min Act: -0.0001

Data Index: 586179 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4967. Min Act: -0.0001

Data Index: 915088 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4653. Min Act: -0.0001

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4442. Min Act: -0.0001

Data Index: 435796 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1084247 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3914. Min Act: -0.0001

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3701. Min Act: -0.0001

Data Index: 1329583 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4154. Min Act: -0.0001

Data Index: 860236 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4175. Min Act: -0.0001

Data Index: 751858 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4269. Min Act: -0.0001

Data Index: 985346 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4481. Min Act: -0.0001

Data Index: 1114039 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3822. Min Act: -0.0001

Data Index: 224867 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3662. Min Act: -0.0001

Data Index: 471575 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1222703 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3744. Min Act: -0.0001

Data Index: 459738 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4014. Min Act: -0.0001

Data Index: 195668 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3670. Min Act: -0.0001

Data Index: 82716 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3768. Min Act: -0.0001

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3848. Min Act: -0.0001

Data Index: 730182 (C4 (Web Text))

Max Activating Token Index: 67