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

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

Neuron 1768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0043. Min Range: -1.0043

Max Act: 1.0043. Min Act: -0.0001

Data Index: 879695 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.9522. Min Act: -0.0001

Data Index: 824431 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.9206. Min Act: -0.0001

Data Index: 476312 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.8835. Min Act: -0.0001

Data Index: 541204 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.8975. Min Act: -0.0001

Data Index: 843279 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.8678. Min Act: -0.0001

Data Index: 728744 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1130828 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1088400 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7859. Min Act: -0.0001

Data Index: 83439 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.8403. Min Act: -0.0001

Data Index: 949642 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7958. Min Act: -0.0001

Data Index: 1160935 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7940. Min Act: -0.0001

Data Index: 868329 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7621. Min Act: -0.0001

Data Index: 562540 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7848. Min Act: -0.0001

Data Index: 806616 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7261. Min Act: -0.0001

Data Index: 218880 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7447. Min Act: -0.0001

Data Index: 990306 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7939. Min Act: -0.0001

Data Index: 601662 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7611. Min Act: -0.0001

Data Index: 219011 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7475. Min Act: -0.0001

Data Index: 282153 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 1.0043. Min Range: -1.0043

Max Act: 0.7406. Min Act: -0.0001

Data Index: 71186 (C4 (Web Text))

Max Activating Token Index: 544