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

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

Neuron 141 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: 0.9050. Min Range: -0.9050

Max Act: 0.7434. Min Act: -0.0000

Data Index: 344233 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1350394 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8090. Min Act: -0.0001

Data Index: 8336 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1269060 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1200169 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8023. Min Act: -0.0000

Data Index: 227977 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1345699 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7519. Min Act: -0.0000

Data Index: 303720 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1976 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7182. Min Act: -0.0000

Data Index: 542036 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6678. Min Act: -0.0001

Data Index: 635310 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6657. Min Act: -0.0000

Data Index: 10241 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6507. Min Act: -0.0000

Data Index: 359841 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6280. Min Act: -0.0000

Data Index: 9234 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6656. Min Act: -0.0000

Data Index: 837738 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6281. Min Act: -0.0000

Data Index: 683380 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6464. Min Act: -0.0000

Data Index: 131825 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6175. Min Act: -0.0000

Data Index: 622666 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6406. Min Act: -0.0000

Data Index: 697341 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6525. Min Act: -0.0000

Data Index: 886917 (C4 (Web Text))

Max Activating Token Index: 187