Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9110. Min Act: -0.0001

Data Index: 100447 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9036. Min Act: -0.0001

Data Index: 1453033 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1254928 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1457104 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8736. Min Act: -0.0001

Data Index: 1429650 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8182. Min Act: -0.0001

Data Index: 1403248 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1510543 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9057. Min Act: -0.0001

Data Index: 893785 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1572812 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7765. Min Act: -0.0001

Data Index: 1384956 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1447170 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8355. Min Act: -0.0001

Data Index: 1614643 (Python Code)

Max Activating Token Index: 347

Text #12

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6890. Min Act: -0.0001

Data Index: 170799 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7531. Min Act: -0.0001

Data Index: 1615008 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1649101 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1633027 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1436233 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7050. Min Act: -0.0001

Data Index: 915259 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1537506 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1656940 (Python Code)

Max Activating Token Index: 929