Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4162 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1217887 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3659. Min Act: -0.0000

Data Index: 543100 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1308214 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1250270 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3216. Min Act: -0.0000

Data Index: 663489 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1309192 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3014. Min Act: -0.0000

Data Index: 666081 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2992. Min Act: -0.0000

Data Index: 137981 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3182. Min Act: -0.0000

Data Index: 404382 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1132214 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2978. Min Act: -0.0000

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1003938 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1056860 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3157. Min Act: -0.0000

Data Index: 85563 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1096981 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1182418 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2842. Min Act: -0.0000

Data Index: 767066 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2836. Min Act: -0.0000

Data Index: 207047 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1333 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2707. Min Act: -0.0000

Data Index: 371718 (C4 (Web Text))

Max Activating Token Index: 314