Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7453. Min Act: -0.0000

Data Index: 456502 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6306. Min Act: -0.0001

Data Index: 1324645 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5986. Min Act: -0.0000

Data Index: 904832 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6020. Min Act: -0.0000

Data Index: 571656 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1041411 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6422. Min Act: -0.0000

Data Index: 773793 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5946. Min Act: -0.0001

Data Index: 669380 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6071. Min Act: -0.0000

Data Index: 928949 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1154000 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6059. Min Act: -0.0001

Data Index: 955011 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6563. Min Act: -0.0001

Data Index: 232147 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5960. Min Act: -0.0000

Data Index: 698394 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5905. Min Act: -0.0000

Data Index: 884248 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6280. Min Act: -0.0000

Data Index: 883131 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5969. Min Act: -0.0000

Data Index: 107563 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5801. Min Act: -0.0000

Data Index: 788104 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1121914 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1211543 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5559. Min Act: -0.0000

Data Index: 158617 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5222. Min Act: -0.0000

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 602