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

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

Neuron 4696 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: 4.4932. Min Range: -4.4932

Max Act: 4.4932. Min Act: -0.0001

Data Index: 449590 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 4.4932. Min Range: -4.4932

Max Act: 4.3048. Min Act: -0.0001

Data Index: 1293821 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 4.4932. Min Range: -4.4932

Max Act: 4.3759. Min Act: -0.0000

Data Index: 1055696 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 4.4932. Min Range: -4.4932

Max Act: 4.3815. Min Act: -0.0000

Data Index: 1114273 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 4.4932. Min Range: -4.4932

Max Act: 4.1473. Min Act: -0.0001

Data Index: 125952 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 4.4932. Min Range: -4.4932

Max Act: 4.3039. Min Act: -0.0001

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 4.4932. Min Range: -4.4932

Max Act: 3.9391. Min Act: -0.0000

Data Index: 1088104 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 4.4932. Min Range: -4.4932

Max Act: 3.8150. Min Act: -0.0000

Data Index: 1171725 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 4.4932. Min Range: -4.4932

Max Act: 3.3202. Min Act: -0.0001

Data Index: 304076 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 4.4932. Min Range: -4.4932

Max Act: 3.2677. Min Act: -0.0000

Data Index: 201724 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.9286. Min Act: -0.0000

Data Index: 1237610 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.8819. Min Act: -0.0000

Data Index: 28762 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.8503. Min Act: -0.0001

Data Index: 193057 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.5863. Min Act: -0.0000

Data Index: 1101602 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.9509. Min Act: -0.0001

Data Index: 385330 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 4.4932. Min Range: -4.4932

Max Act: 3.0506. Min Act: -0.0000

Data Index: 400309 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.8892. Min Act: -0.0001

Data Index: 504844 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.8863. Min Act: -0.0000

Data Index: 1111142 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.6263. Min Act: -0.0000

Data Index: 1195991 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 4.4932. Min Range: -4.4932

Max Act: 2.8863. Min Act: -0.0000

Data Index: 257354 (C4 (Web Text))

Max Activating Token Index: 673