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

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

Neuron 4428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.5170. Min Act: -0.0001

Data Index: 1218135 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.5291. Min Act: -0.0001

Data Index: 731206 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1346852 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4642. Min Act: -0.0001

Data Index: 29791 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4823. Min Act: -0.0001

Data Index: 798109 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4255. Min Act: -0.0001

Data Index: 264685 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1245900 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4996. Min Act: -0.0001

Data Index: 556747 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.3939. Min Act: -0.0001

Data Index: 224933 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4616. Min Act: -0.0001

Data Index: 428321 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1073464 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4157. Min Act: -0.0001

Data Index: 643390 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4096. Min Act: -0.0001

Data Index: 793379 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4572. Min Act: -0.0001

Data Index: 761596 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1011568 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4303. Min Act: -0.0001

Data Index: 899122 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4112. Min Act: -0.0001

Data Index: 473401 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.3845. Min Act: -0.0001

Data Index: 806584 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.3871. Min Act: -0.0001

Data Index: 540778 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.5291. Min Range: -0.5291

Max Act: 0.4093. Min Act: -0.0001

Data Index: 776423 (C4 (Web Text))

Max Activating Token Index: 645