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

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

Neuron 2445 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: 0.6822. Min Range: -0.6822

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1187080 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6503. Min Act: -0.0001

Data Index: 1197778 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1136090 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6252. Min Act: -0.0001

Data Index: 303758 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6047. Min Act: -0.0001

Data Index: 931754 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5788. Min Act: -0.0001

Data Index: 962632 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6020. Min Act: -0.0001

Data Index: 455479 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5919. Min Act: -0.0001

Data Index: 96008 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5922. Min Act: -0.0001

Data Index: 796356 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6030. Min Act: -0.0001

Data Index: 631746 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6012. Min Act: -0.0001

Data Index: 869428 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5819. Min Act: -0.0001

Data Index: 819225 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5970. Min Act: -0.0001

Data Index: 92922 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1356095 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5919. Min Act: -0.0001

Data Index: 810634 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5928. Min Act: -0.0001

Data Index: 295341 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5854. Min Act: -0.0001

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5779. Min Act: -0.0001

Data Index: 294843 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5576. Min Act: -0.0001

Data Index: 1290009 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5555. Min Act: -0.0001

Data Index: 971716 (C4 (Web Text))

Max Activating Token Index: 682