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

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

Neuron 5556 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7939. Min Range: -4.7939

Max Act: 4.7939. Min Act: -0.0000

Data Index: 777570 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 4.7939. Min Range: -4.7939

Max Act: 4.0562. Min Act: -0.0000

Data Index: 801768 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.9779. Min Act: -0.0000

Data Index: 592702 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.7887. Min Act: -0.0000

Data Index: 145764 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.8879. Min Act: -0.0000

Data Index: 568794 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.8793. Min Act: -0.0000

Data Index: 282393 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.6656. Min Act: -0.0000

Data Index: 530394 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.7961. Min Act: -0.0000

Data Index: 1031943 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.7995. Min Act: -0.0000

Data Index: 895712 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.7804. Min Act: -0.0000

Data Index: 901569 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.2602. Min Act: -0.0000

Data Index: 767154 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.5406. Min Act: -0.0000

Data Index: 913412 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.4770. Min Act: -0.0000

Data Index: 1106104 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.2963. Min Act: -0.0000

Data Index: 495147 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.4264. Min Act: -0.0000

Data Index: 713315 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.4197. Min Act: -0.0000

Data Index: 78308 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.4104. Min Act: -0.0000

Data Index: 1078280 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.3746. Min Act: -0.0000

Data Index: 1321340 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.4048. Min Act: -0.0000

Data Index: 539130 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 4.7939. Min Range: -4.7939

Max Act: 3.3458. Min Act: -0.0000

Data Index: 1021665 (C4 (Web Text))

Max Activating Token Index: 647