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

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

Neuron 1906 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9981. Min Act: -0.0000

Data Index: 1320159 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 2.0404. Min Range: -2.0404

Max Act: 2.0404. Min Act: -0.0001

Data Index: 827361 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9649. Min Act: -0.0000

Data Index: 78315 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9663. Min Act: -0.0001

Data Index: 1073307 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9358. Min Act: -0.0001

Data Index: 851580 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9986. Min Act: -0.0000

Data Index: 639080 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.9406. Min Act: -0.0000

Data Index: 219430 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1140617 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.8184. Min Act: -0.0000

Data Index: 683109 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.8930. Min Act: -0.0000

Data Index: 369666 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.8001. Min Act: -0.0000

Data Index: 937068 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7880. Min Act: -0.0001

Data Index: 335138 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.8360. Min Act: -0.0000

Data Index: 253329 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7285. Min Act: -0.0000

Data Index: 321118 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7272. Min Act: -0.0000

Data Index: 1319751 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1290156 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7387. Min Act: -0.0000

Data Index: 197053 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.6605. Min Act: -0.0001

Data Index: 595044 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.6873. Min Act: -0.0001

Data Index: 1287116 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 2.0404. Min Range: -2.0404

Max Act: 1.7199. Min Act: -0.0000

Data Index: 378807 (C4 (Web Text))

Max Activating Token Index: 199