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

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

Neuron 670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.5023. Min Act: -0.0001

Data Index: 380556 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.4182. Min Act: -0.0001

Data Index: 195056 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.3915. Min Act: -0.0001

Data Index: 1090758 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.1806. Min Act: -0.0000

Data Index: 189300 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.1771. Min Act: -0.0001

Data Index: 547789 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.1394. Min Act: -0.0001

Data Index: 1210351 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.0734. Min Act: -0.0001

Data Index: 1326130 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.1307. Min Act: -0.0001

Data Index: 30906 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.8444. Min Act: -0.0001

Data Index: 1331334 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.8197. Min Act: -0.0001

Data Index: 667960 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.0983. Min Act: -0.0001

Data Index: 119127 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.7055. Min Act: -0.0001

Data Index: 908811 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.1167. Min Act: -0.0001

Data Index: 949451 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.0928. Min Act: -0.0001

Data Index: 587494 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.9677. Min Act: -0.0001

Data Index: 1320950 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.9309. Min Act: -0.0001

Data Index: 45357 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.9510. Min Act: -0.0001

Data Index: 190502 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.9284. Min Act: -0.0001

Data Index: 1304108 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 3.5023. Min Range: -3.5023

Max Act: 2.9481. Min Act: -0.0000

Data Index: 807844 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.5023. Min Range: -3.5023

Max Act: 3.0630. Min Act: -0.0001

Data Index: 150196 (C4 (Web Text))

Max Activating Token Index: 79