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

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

Neuron 798 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: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 895933 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8491. Min Act: -0.0000

Data Index: 526702 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8583. Min Act: -0.0000

Data Index: 884743 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1149489 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7793. Min Act: -0.0000

Data Index: 708401 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7506. Min Act: -0.0000

Data Index: 532838 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7992. Min Act: -0.0000

Data Index: 813783 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7794. Min Act: -0.0000

Data Index: 702435 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7212. Min Act: -0.0000

Data Index: 64951 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7677. Min Act: -0.0000

Data Index: 7027 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1601443 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7126. Min Act: -0.0000

Data Index: 133401 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1211650 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7469. Min Act: -0.0000

Data Index: 982782 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1201441 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8071. Min Act: -0.0000

Data Index: 781113 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7087. Min Act: -0.0000

Data Index: 101948 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6754. Min Act: -0.0000

Data Index: 700427 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1340138 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6893. Min Act: -0.0000

Data Index: 340587 (C4 (Web Text))

Max Activating Token Index: 792