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

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

Neuron 2725 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0001

Data Index: 486385 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0882. Min Act: -0.0001

Data Index: 968103 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0839. Min Act: -0.0001

Data Index: 510124 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0812. Min Act: -0.0001

Data Index: 438083 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1192095 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0839. Min Act: -0.0001

Data Index: 937071 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0856. Min Act: -0.0001

Data Index: 138643 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1071457 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0776. Min Act: -0.0001

Data Index: 103438 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0889. Min Act: -0.0001

Data Index: 486071 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0858. Min Act: -0.0001

Data Index: 922251 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1098 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0853. Min Act: -0.0001

Data Index: 487190 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0778. Min Act: -0.0001

Data Index: 711077 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0812. Min Act: -0.0001

Data Index: 514371 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1155427 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1358110 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0791. Min Act: -0.0001

Data Index: 380065 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1206728 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0728. Min Act: -0.0001

Data Index: 249909 (C4 (Web Text))

Max Activating Token Index: 938