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

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

Neuron 2005 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.4993. Min Act: -0.0001

Data Index: 1152313 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.4112. Min Act: -0.0001

Data Index: 122876 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.2005. Min Act: -0.0001

Data Index: 547225 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.2747. Min Act: -0.0001

Data Index: 531831 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.2690. Min Act: -0.0001

Data Index: 31625 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1662. Min Act: -0.0001

Data Index: 987834 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1895. Min Act: -0.0001

Data Index: 237603 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1882. Min Act: -0.0001

Data Index: 1149860 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1748. Min Act: -0.0001

Data Index: 460841 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1414. Min Act: -0.0001

Data Index: 1197415 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1441. Min Act: -0.0001

Data Index: 960390 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1989. Min Act: -0.0001

Data Index: 1143551 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1826. Min Act: -0.0001

Data Index: 683554 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.0955. Min Act: -0.0001

Data Index: 805315 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1541. Min Act: -0.0001

Data Index: 430656 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.2210. Min Act: -0.0001

Data Index: 474283 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.0393. Min Act: -0.0001

Data Index: 235797 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1001. Min Act: -0.0001

Data Index: 45486 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1667. Min Act: -0.0001

Data Index: 713963 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.4993. Min Range: -1.4993

Max Act: 1.1181. Min Act: -0.0001

Data Index: 699834 (C4 (Web Text))

Max Activating Token Index: 390