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

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

Neuron 304 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: 0.4776. Min Range: -0.4776

Max Act: 0.4671. Min Act: -0.0001

Data Index: 55234 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4776. Min Act: -0.0001

Data Index: 275901 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4570. Min Act: -0.0001

Data Index: 53867 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4402. Min Act: -0.0001

Data Index: 947866 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4278. Min Act: -0.0001

Data Index: 450567 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3997. Min Act: -0.0001

Data Index: 898782 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3813. Min Act: -0.0001

Data Index: 769846 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4058. Min Act: -0.0001

Data Index: 617288 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4015. Min Act: -0.0001

Data Index: 240583 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1087821 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4192. Min Act: -0.0001

Data Index: 1280440 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3794. Min Act: -0.0001

Data Index: 407710 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4055. Min Act: -0.0001

Data Index: 278999 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3956. Min Act: -0.0001

Data Index: 100683 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3703. Min Act: -0.0001

Data Index: 203904 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3849. Min Act: -0.0001

Data Index: 476127 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3973. Min Act: -0.0001

Data Index: 159827 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3777. Min Act: -0.0001

Data Index: 934396 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3676. Min Act: -0.0001

Data Index: 616032 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3917. Min Act: -0.0001

Data Index: 246088 (C4 (Web Text))

Max Activating Token Index: 966