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

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

Neuron 1804 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: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0001

Data Index: 208056 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1176230 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1140651 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1298484 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1127. Min Act: -0.0001

Data Index: 953699 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1098. Min Act: -0.0001

Data Index: 881567 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1021. Min Act: -0.0001

Data Index: 835284 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1162. Min Act: -0.0002

Data Index: 436059 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1317045 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1218934 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1024. Min Act: -0.0002

Data Index: 371576 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1326289 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1036. Min Act: -0.0002

Data Index: 550026 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1042. Min Act: -0.0002

Data Index: 343476 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1055. Min Act: -0.0002

Data Index: 164367 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0938. Min Act: -0.0001

Data Index: 105028 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1013. Min Act: -0.0001

Data Index: 399485 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0968. Min Act: -0.0001

Data Index: 739241 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0999. Min Act: -0.0001

Data Index: 406708 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0996. Min Act: -0.0001

Data Index: 456917 (C4 (Web Text))

Max Activating Token Index: 639