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

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

Neuron 2138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3021. Min Range: -2.3021

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1453528 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.5694. Min Act: -0.0000

Data Index: 1372716 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 2.3021. Min Range: -2.3021

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1653909 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1606810 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.9402. Min Act: -0.0000

Data Index: 1656594 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1615767 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1532235 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1366122 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1591208 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.8364. Min Act: -0.0000

Data Index: 77486 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 2.3021. Min Range: -2.3021

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1387818 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7203. Min Act: -0.0000

Data Index: 1412112 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.6788. Min Act: -0.0000

Data Index: 737010 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1361399 (Python Code)

Max Activating Token Index: 407

Text #14

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7276. Min Act: -0.0000

Data Index: 607104 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7165. Min Act: -0.0000

Data Index: 1566064 (Python Code)

Max Activating Token Index: 585

Text #16

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1383952 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1589189 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.6094. Min Act: -0.0000

Data Index: 1400971 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 2.3021. Min Range: -2.3021

Max Act: 1.8004. Min Act: -0.0000

Data Index: 1554486 (Python Code)

Max Activating Token Index: 761