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

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

Neuron 1477 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: 0.4094. Min Range: -0.4094

Max Act: 0.4094. Min Act: 0.0000

Data Index: 1011348 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3598. Min Act: -0.0000

Data Index: 389233 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3291. Min Act: -0.0001

Data Index: 838264 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3470. Min Act: -0.0001

Data Index: 458800 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1392216 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3166. Min Act: -0.0001

Data Index: 85753 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3365. Min Act: -0.0001

Data Index: 714102 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3256. Min Act: -0.0000

Data Index: 190043 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3228. Min Act: -0.0001

Data Index: 723657 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3076. Min Act: -0.0000

Data Index: 612094 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3058. Min Act: -0.0001

Data Index: 308751 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1088820 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2811. Min Act: -0.0000

Data Index: 663057 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2861. Min Act: -0.0000

Data Index: 55283 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1277515 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1443402 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1051139 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1449239 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2747. Min Act: -0.0000

Data Index: 392870 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.4094. Min Range: -0.4094

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1160651 (C4 (Web Text))

Max Activating Token Index: 229