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

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

Neuron 6102 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6931. Min Range: -4.6931

Max Act: 4.5100. Min Act: -0.0001

Data Index: 225709 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 4.6931. Min Range: -4.6931

Max Act: 4.6931. Min Act: -0.0001

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 4.6931. Min Range: -4.6931

Max Act: 4.0013. Min Act: -0.0001

Data Index: 371192 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 4.6931. Min Range: -4.6931

Max Act: 4.3371. Min Act: -0.0000

Data Index: 406694 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 4.6931. Min Range: -4.6931

Max Act: 3.1307. Min Act: -0.0000

Data Index: 1320772 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 4.6931. Min Range: -4.6931

Max Act: 2.9716. Min Act: -0.0001

Data Index: 965947 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 4.6931. Min Range: -4.6931

Max Act: 2.8501. Min Act: -0.0001

Data Index: 193005 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 4.6931. Min Range: -4.6931

Max Act: 2.7469. Min Act: -0.0001

Data Index: 676300 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 4.6931. Min Range: -4.6931

Max Act: 2.2881. Min Act: -0.0001

Data Index: 643390 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 4.6931. Min Range: -4.6931

Max Act: 2.0171. Min Act: -0.0001

Data Index: 241192 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.9656. Min Act: -0.0001

Data Index: 451051 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.8427. Min Act: -0.0001

Data Index: 1620886 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.7362. Min Act: -0.0001

Data Index: 1435771 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.9233. Min Act: -0.0001

Data Index: 986749 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.8904. Min Act: -0.0001

Data Index: 701918 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.8748. Min Act: -0.0001

Data Index: 1220480 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.8597. Min Act: -0.0001

Data Index: 1231264 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.7207. Min Act: -0.0001

Data Index: 1655135 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.8135. Min Act: -0.0000

Data Index: 14747 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 4.6931. Min Range: -4.6931

Max Act: 1.7446. Min Act: -0.0001

Data Index: 1065981 (C4 (Web Text))

Max Activating Token Index: 404