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

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

Neuron 6006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.9761. Min Act: -0.0001

Data Index: 90709 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.3304. Min Act: -0.0000

Data Index: 1147067 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.1152. Min Act: -0.0000

Data Index: 449162 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.7708. Min Act: -0.0000

Data Index: 1011489 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.0384. Min Act: -0.0000

Data Index: 1016320 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.0973. Min Act: -0.0000

Data Index: 1240184 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.0885. Min Act: -0.0000

Data Index: 645856 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 4.3304. Min Range: -4.3304

Max Act: 4.1124. Min Act: -0.0000

Data Index: 187706 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.5573. Min Act: -0.0000

Data Index: 1351684 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.7336. Min Act: -0.0000

Data Index: 665993 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.2716. Min Act: -0.0000

Data Index: 105681 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.8882. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.6568. Min Act: -0.0000

Data Index: 960017 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.8191. Min Act: -0.0000

Data Index: 673574 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.8162. Min Act: -0.0000

Data Index: 109004 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.9462. Min Act: -0.0000

Data Index: 231452 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.6104. Min Act: -0.0001

Data Index: 605250 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.5527. Min Act: -0.0000

Data Index: 10325 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.5380. Min Act: -0.0000

Data Index: 923450 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 4.3304. Min Range: -4.3304

Max Act: 3.6884. Min Act: -0.0000

Data Index: 532840 (C4 (Web Text))

Max Activating Token Index: 1009