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

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

Neuron 758 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8641. Min Act: -0.0000

Data Index: 684041 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8110. Min Act: -0.0000

Data Index: 577305 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.3459. Min Act: -0.0000

Data Index: 668621 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.4750. Min Act: -0.0000

Data Index: 689469 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0948. Min Act: -0.0000

Data Index: 645001 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.8703. Min Act: -0.0000

Data Index: 1244959 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0839. Min Act: -0.0000

Data Index: 1268613 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.8658. Min Act: -0.0000

Data Index: 112004 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1080266 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1120064 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1241262 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.5922. Min Act: -0.0000

Data Index: 21567 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6519. Min Act: -0.0000

Data Index: 641070 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6779. Min Act: -0.0000

Data Index: 651684 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.3922. Min Act: -0.0000

Data Index: 806896 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.5162. Min Act: -0.0000

Data Index: 1200778 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1061957 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4872. Min Act: -0.0000

Data Index: 632860 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.3735. Min Act: -0.0000

Data Index: 1246524 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4992. Min Act: -0.0000

Data Index: 710095 (C4 (Web Text))

Max Activating Token Index: 766