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

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

Neuron 4387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4156. Min Range: -1.4156

Max Act: 1.4156. Min Act: -0.0000

Data Index: 964269 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 1.4156. Min Range: -1.4156

Max Act: 1.0192. Min Act: -0.0000

Data Index: 892000 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.9561. Min Act: -0.0000

Data Index: 448824 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.9162. Min Act: -0.0000

Data Index: 871838 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1295789 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.8240. Min Act: -0.0000

Data Index: 980220 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1129735 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7830. Min Act: -0.0000

Data Index: 609765 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7927. Min Act: -0.0000

Data Index: 260708 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7646. Min Act: -0.0000

Data Index: 390541 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7093. Min Act: -0.0000

Data Index: 943521 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7543. Min Act: -0.0000

Data Index: 421832 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7780. Min Act: -0.0000

Data Index: 658296 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7548. Min Act: -0.0000

Data Index: 327877 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7197. Min Act: -0.0000

Data Index: 743804 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7139. Min Act: -0.0000

Data Index: 843323 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.7072. Min Act: -0.0000

Data Index: 740814 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1097510 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.6657. Min Act: -0.0000

Data Index: 424198 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.4156. Min Range: -1.4156

Max Act: 0.6395. Min Act: -0.0000

Data Index: 901183 (C4 (Web Text))

Max Activating Token Index: 624