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

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

Neuron 3242 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: 0.6722. Min Range: -0.6722

Max Act: 0.6722. Min Act: -0.0001

Data Index: 287557 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5921. Min Act: -0.0001

Data Index: 1130010 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5887. Min Act: -0.0001

Data Index: 972079 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1220028 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5548. Min Act: -0.0001

Data Index: 47964 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5354. Min Act: -0.0001

Data Index: 66342 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5165. Min Act: -0.0001

Data Index: 84870 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5276. Min Act: -0.0001

Data Index: 229109 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.5395. Min Act: -0.0001

Data Index: 1123765 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4961. Min Act: -0.0001

Data Index: 810362 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4518. Min Act: -0.0002

Data Index: 509952 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4347. Min Act: -0.0001

Data Index: 761775 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4188. Min Act: -0.0002

Data Index: 1082964 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4129. Min Act: -0.0002

Data Index: 689602 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.3990. Min Act: -0.0001

Data Index: 505613 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.3825. Min Act: -0.0002

Data Index: 770201 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4083. Min Act: -0.0001

Data Index: 63606 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.3917. Min Act: -0.0002

Data Index: 1017936 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1208681 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.6722. Min Range: -0.6722

Max Act: 0.3933. Min Act: -0.0001

Data Index: 257095 (C4 (Web Text))

Max Activating Token Index: 582