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

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

Neuron 897 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.8657. Min Act: -0.0000

Data Index: 491030 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.3902. Min Act: -0.0000

Data Index: 1313106 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.5981. Min Act: -0.0000

Data Index: 920910 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.7357. Min Act: -0.0001

Data Index: 152240 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.6565. Min Act: -0.0001

Data Index: 63643 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.5295. Min Act: -0.0000

Data Index: 157791 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4800. Min Act: -0.0001

Data Index: 314166 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.7189. Min Act: -0.0001

Data Index: 920666 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.3915. Min Act: -0.0000

Data Index: 993771 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4971. Min Act: -0.0000

Data Index: 301612 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.3662. Min Act: -0.0001

Data Index: 462874 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4541. Min Act: -0.0000

Data Index: 444936 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.2825. Min Act: -0.0000

Data Index: 535310 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.5323. Min Act: -0.0000

Data Index: 465531 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1072033 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4172. Min Act: -0.0001

Data Index: 206438 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.3893. Min Act: -0.0000

Data Index: 870181 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.3899. Min Act: -0.0001

Data Index: 109800 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.3897. Min Act: -0.0001

Data Index: 261564 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 3.8657. Min Range: -3.8657

Max Act: 2.4422. Min Act: -0.0000

Data Index: 415480 (C4 (Web Text))

Max Activating Token Index: 327