Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1441. Min Act: -0.0001

Data Index: 103802 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1165. Min Act: -0.0000

Data Index: 867935 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1178. Min Act: -0.0000

Data Index: 576146 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1062. Min Act: -0.0000

Data Index: 713384 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1026819 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1030. Min Act: -0.0000

Data Index: 574335 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1401868 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1050. Min Act: -0.0000

Data Index: 2468 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1457731 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1010. Min Act: -0.0001

Data Index: 600107 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1541971 (Python Code)

Max Activating Token Index: 922

Text #11

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1161420 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1447133 (Python Code)

Max Activating Token Index: 741

Text #13

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1031. Min Act: -0.0000

Data Index: 260682 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1186084 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1240501 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1216773 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1570230 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1422755 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1397183 (Python Code)

Max Activating Token Index: 602