Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1609735 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1487855 (Python Code)

Max Activating Token Index: 187

Text #2

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1301016 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1426508 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4631. Min Act: -0.0000

Data Index: 678971 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1400875 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1538058 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1593174 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1589095 (Python Code)

Max Activating Token Index: 601

Text #9

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1557837 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1540828 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1548665 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1575608 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1610706 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1398602 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1617767 (Python Code)

Max Activating Token Index: 486

Text #16

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1474023 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1638067 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4123. Min Act: -0.0000

Data Index: 244434 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1549193 (Python Code)

Max Activating Token Index: 131