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

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

Neuron 3451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6160. Min Range: -5.6160

Max Act: 5.6160. Min Act: -0.0001

Data Index: 692186 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 5.6160. Min Range: -5.6160

Max Act: 5.3470. Min Act: -0.0000

Data Index: 432502 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.8689. Min Act: -0.0001

Data Index: 373634 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.4562. Min Act: -0.0000

Data Index: 1280871 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.8247. Min Act: -0.0000

Data Index: 975879 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.4422. Min Act: -0.0000

Data Index: 795612 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.5545. Min Act: -0.0000

Data Index: 857948 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.3711. Min Act: -0.0000

Data Index: 944150 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.6962. Min Act: -0.0000

Data Index: 114835 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 5.6160. Min Range: -5.6160

Max Act: 3.9727. Min Act: -0.0000

Data Index: 1115664 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.3918. Min Act: -0.0000

Data Index: 12867 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.5385. Min Act: -0.0000

Data Index: 137225 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.3590. Min Act: -0.0001

Data Index: 1192930 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.3696. Min Act: -0.0001

Data Index: 347314 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.3325. Min Act: -0.0000

Data Index: 367068 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.4655. Min Act: -0.0001

Data Index: 282032 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 5.6160. Min Range: -5.6160

Max Act: 3.9457. Min Act: -0.0001

Data Index: 330391 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.2914. Min Act: -0.0000

Data Index: 936940 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.2519. Min Act: -0.0000

Data Index: 706298 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 5.6160. Min Range: -5.6160

Max Act: 4.0483. Min Act: -0.0000

Data Index: 484643 (C4 (Web Text))

Max Activating Token Index: 892