Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2095 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0400. Min Range: -1.0400

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1199868 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.0400. Min Range: -1.0400

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1162693 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9674. Min Act: -0.0001

Data Index: 59050 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9696. Min Act: -0.0001

Data Index: 504106 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9536. Min Act: -0.0001

Data Index: 196966 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9070. Min Act: -0.0001

Data Index: 333816 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9080. Min Act: -0.0001

Data Index: 373522 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1313832 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8195. Min Act: -0.0001

Data Index: 340594 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7841. Min Act: -0.0001

Data Index: 968758 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8269. Min Act: -0.0001

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1306415 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7823. Min Act: -0.0001

Data Index: 193505 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1342039 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1060633 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7977. Min Act: -0.0001

Data Index: 1003448 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8134. Min Act: -0.0001

Data Index: 882865 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1228282 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8631. Min Act: -0.0001

Data Index: 726071 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8016. Min Act: -0.0001

Data Index: 768486 (C4 (Web Text))

Max Activating Token Index: 655