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

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

Neuron 707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6894. Min Act: -0.0001

Data Index: 466500 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1121111 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6440. Min Act: -0.0001

Data Index: 1274604 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6370. Min Act: -0.0001

Data Index: 555067 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6343. Min Act: -0.0001

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6094. Min Act: -0.0001

Data Index: 438724 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6276. Min Act: -0.0001

Data Index: 223003 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6160. Min Act: -0.0001

Data Index: 47225 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6197. Min Act: -0.0001

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5916. Min Act: -0.0001

Data Index: 792202 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5960. Min Act: -0.0001

Data Index: 959801 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1153613 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6431. Min Act: -0.0001

Data Index: 342718 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5965. Min Act: -0.0002

Data Index: 985888 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6260. Min Act: -0.0001

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6196. Min Act: -0.0001

Data Index: 852646 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6227. Min Act: -0.0002

Data Index: 482272 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5949. Min Act: -0.0001

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5905. Min Act: -0.0001

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6125. Min Act: -0.0001

Data Index: 713145 (C4 (Web Text))

Max Activating Token Index: 683