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

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

Neuron 457 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0001

Data Index: 499248 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9177. Min Act: -0.0001

Data Index: 1118562 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8178. Min Act: -0.0001

Data Index: 595408 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1140116 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7626. Min Act: -0.0001

Data Index: 15699 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1264971 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7451. Min Act: -0.0001

Data Index: 802922 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1238428 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7797. Min Act: -0.0001

Data Index: 690940 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7106. Min Act: -0.0001

Data Index: 1211405 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7722. Min Act: -0.0001

Data Index: 702446 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7301. Min Act: -0.0001

Data Index: 251738 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7360. Min Act: -0.0001

Data Index: 896454 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7310. Min Act: -0.0001

Data Index: 281898 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7094. Min Act: -0.0001

Data Index: 1109819 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1078503 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6911. Min Act: -0.0001

Data Index: 789877 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7368. Min Act: -0.0001

Data Index: 870838 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6576. Min Act: -0.0001

Data Index: 265552 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1250939 (C4 (Web Text))

Max Activating Token Index: 121