Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0070. Min Range: -2.0070

Max Act: 2.0070. Min Act: -0.0000

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1006833 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.6280. Min Act: -0.0000

Data Index: 499316 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.6194. Min Act: -0.0000

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1104886 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5863. Min Act: -0.0000

Data Index: 913062 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.6731. Min Act: -0.0000

Data Index: 380236 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1578600 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5510. Min Act: -0.0000

Data Index: 790461 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5363. Min Act: -0.0000

Data Index: 330637 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5421. Min Act: -0.0000

Data Index: 325357 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5898. Min Act: -0.0000

Data Index: 29910 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5307. Min Act: -0.0000

Data Index: 1320083 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5360. Min Act: -0.0000

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1399991 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1493435 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.5533. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.4570. Min Act: -0.0000

Data Index: 245851 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 2.0070. Min Range: -2.0070

Max Act: 1.4899. Min Act: -0.0000

Data Index: 1580836 (Python Code)

Max Activating Token Index: 943