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

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

Neuron 1672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1245. Min Act: -0.0001

Data Index: 704952 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1558. Min Act: -0.0001

Data Index: 1193453 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1682. Min Act: -0.0002

Data Index: 731669 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1586. Min Act: -0.0002

Data Index: 127231 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1137. Min Act: -0.0001

Data Index: 424798 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0637. Min Act: -0.0001

Data Index: 22479 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0099. Min Act: -0.0002

Data Index: 301453 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0330. Min Act: -0.0002

Data Index: 486045 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9858. Min Act: -0.0002

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0958. Min Act: -0.0002

Data Index: 1075599 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0358. Min Act: -0.0002

Data Index: 1065784 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0567. Min Act: -0.0002

Data Index: 867580 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0620. Min Act: -0.0002

Data Index: 1136816 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0109. Min Act: -0.0002

Data Index: 539149 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1089. Min Act: -0.0001

Data Index: 766095 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9694. Min Act: -0.0002

Data Index: 194536 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0082. Min Act: -0.0002

Data Index: 400700 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9498. Min Act: -0.0002

Data Index: 848063 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9453. Min Act: -0.0002

Data Index: 831688 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0939. Min Act: -0.0002

Data Index: 575536 (C4 (Web Text))

Max Activating Token Index: 177