Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2001. Min Range: -2.2001

Max Act: 2.2001. Min Act: -0.0001

Data Index: 809464 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 2.2001. Min Range: -2.2001

Max Act: 2.0657. Min Act: -0.0001

Data Index: 526830 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.9785. Min Act: -0.0000

Data Index: 732380 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.8873. Min Act: -0.0001

Data Index: 642221 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.6489. Min Act: -0.0000

Data Index: 90569 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.7069. Min Act: -0.0000

Data Index: 690304 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.6057. Min Act: -0.0001

Data Index: 783255 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4451. Min Act: -0.0000

Data Index: 59669 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4681. Min Act: -0.0000

Data Index: 556047 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.6198. Min Act: -0.0000

Data Index: 872993 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1152836 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4462. Min Act: -0.0000

Data Index: 140586 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4207. Min Act: -0.0000

Data Index: 216581 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1242613 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.3697. Min Act: -0.0001

Data Index: 1185004 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4448. Min Act: -0.0000

Data Index: 294755 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.4039. Min Act: -0.0001

Data Index: 755175 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.3557. Min Act: -0.0000

Data Index: 156221 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.3875. Min Act: -0.0000

Data Index: 160514 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.2001. Min Range: -2.2001

Max Act: 1.3454. Min Act: -0.0000

Data Index: 673289 (C4 (Web Text))

Max Activating Token Index: 843