Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5729 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9175. Min Act: 0.0000

Data Index: 947792 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 2.1039. Min Range: -2.1039

Max Act: 2.1039. Min Act: 0.0000

Data Index: 159644 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8663. Min Act: 0.0000

Data Index: 425976 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7184. Min Act: 0.0001

Data Index: 1258946 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6926. Min Act: -0.0000

Data Index: 590675 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6832. Min Act: -0.0000

Data Index: 1349668 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6620. Min Act: -0.0000

Data Index: 983420 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6423. Min Act: -0.0000

Data Index: 503414 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6352. Min Act: -0.0000

Data Index: 523041 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.6078. Min Act: 0.0001

Data Index: 335013 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.5266. Min Act: 0.0001

Data Index: 328299 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.5132. Min Act: 0.0000

Data Index: 876063 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.4093. Min Act: 0.0000

Data Index: 316775 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.4818. Min Act: 0.0000

Data Index: 1268192 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.4609. Min Act: 0.0000

Data Index: 227689 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.3663. Min Act: -0.0000

Data Index: 911212 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.3613. Min Act: 0.0000

Data Index: 624303 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.3350. Min Act: 0.0000

Data Index: 650536 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.3094. Min Act: -0.0000

Data Index: 506555 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.3038. Min Act: 0.0000

Data Index: 551183 (C4 (Web Text))

Max Activating Token Index: 324