Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2555 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.9221. Min Act: -0.0001

Data Index: 904377 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1196828 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5749. Min Act: -0.0001

Data Index: 525341 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1147864 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5718. Min Act: -0.0001

Data Index: 556215 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5616. Min Act: -0.0001

Data Index: 3959 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5474. Min Act: -0.0001

Data Index: 833567 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1353808 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5433. Min Act: -0.0001

Data Index: 835104 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5432. Min Act: -0.0001

Data Index: 784179 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5253. Min Act: -0.0001

Data Index: 1096336 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5315. Min Act: -0.0001

Data Index: 418196 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5217. Min Act: -0.0001

Data Index: 447869 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5517. Min Act: -0.0001

Data Index: 732861 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1130677 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5078. Min Act: -0.0001

Data Index: 614043 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1329171 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5216. Min Act: -0.0001

Data Index: 225523 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.5031. Min Act: -0.0001

Data Index: 256233 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.4991. Min Act: -0.0001

Data Index: 472356 (C4 (Web Text))

Max Activating Token Index: 502