Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 553 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4811. Min Act: -0.0001

Data Index: 217143 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6875. Min Act: -0.0001

Data Index: 1354310 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5073. Min Act: -0.0001

Data Index: 437836 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.3811. Min Act: -0.0001

Data Index: 910972 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.3667. Min Act: -0.0001

Data Index: 173128 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4221. Min Act: -0.0001

Data Index: 1346401 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.3224. Min Act: -0.0001

Data Index: 1257691 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.2995. Min Act: -0.0001

Data Index: 744992 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.1366. Min Act: -0.0001

Data Index: 775785 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.9766. Min Act: -0.0001

Data Index: 531550 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.8939. Min Act: -0.0001

Data Index: 134937 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.0438. Min Act: -0.0001

Data Index: 697069 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.1409. Min Act: -0.0001

Data Index: 1020584 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.0240. Min Act: -0.0001

Data Index: 613384 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.2766. Min Act: -0.0001

Data Index: 1253490 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.1055. Min Act: -0.0001

Data Index: 1141129 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.9655. Min Act: -0.0001

Data Index: 205051 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.0719. Min Act: -0.0001

Data Index: 1046255 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.2138. Min Act: -0.0001

Data Index: 1336350 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.0443. Min Act: -0.0001

Data Index: 464146 (C4 (Web Text))

Max Activating Token Index: 705