Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4363 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2097. Min Range: -1.2097

Max Act: 1.2097. Min Act: -0.0000

Data Index: 847401 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.2097. Min Range: -1.2097

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1167623 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8984. Min Act: -0.0000

Data Index: 504396 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.9792. Min Act: -0.0000

Data Index: 505809 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.9376. Min Act: -0.0000

Data Index: 652758 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1235683 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8740. Min Act: -0.0000

Data Index: 651085 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8251. Min Act: -0.0000

Data Index: 971835 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8026. Min Act: -0.0000

Data Index: 627497 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7934. Min Act: -0.0000

Data Index: 170602 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8148. Min Act: -0.0000

Data Index: 52512 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1268263 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8008. Min Act: -0.0000

Data Index: 668256 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1013618 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1161971 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7461. Min Act: -0.0000

Data Index: 456251 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7499. Min Act: -0.0000

Data Index: 398235 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7701. Min Act: -0.0000

Data Index: 181706 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7437. Min Act: -0.0000

Data Index: 282802 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7068. Min Act: -0.0000

Data Index: 572883 (C4 (Web Text))

Max Activating Token Index: 333