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

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

Neuron 5066 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: 2.2118. Min Range: -2.2118

Max Act: 2.1461. Min Act: -0.0000

Data Index: 114853 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0069. Min Act: -0.0000

Data Index: 1361278 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.1029. Min Act: -0.0000

Data Index: 921195 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0672. Min Act: -0.0000

Data Index: 683545 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.2118. Min Act: -0.0000

Data Index: 1183084 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0542. Min Act: -0.0000

Data Index: 1142295 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0371. Min Act: -0.0000

Data Index: 172854 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0312. Min Act: -0.0000

Data Index: 909023 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0086. Min Act: -0.0000

Data Index: 848684 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0152. Min Act: -0.0000

Data Index: 1011686 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9003. Min Act: -0.0000

Data Index: 1315400 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0089. Min Act: -0.0000

Data Index: 557976 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0117. Min Act: -0.0000

Data Index: 1545023 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9952. Min Act: -0.0000

Data Index: 705381 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9809. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9904. Min Act: -0.0000

Data Index: 120731 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9670. Min Act: -0.0000

Data Index: 788280 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.8552. Min Act: -0.0000

Data Index: 683307 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.2118. Min Range: -2.2118

Max Act: 1.9776. Min Act: -0.0000

Data Index: 1141216 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 2.2118. Min Range: -2.2118

Max Act: 2.0908. Min Act: -0.0000

Data Index: 163037 (C4 (Web Text))

Max Activating Token Index: 876