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

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

Neuron 3611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.5048. Min Act: 0.0001

Data Index: 360377 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.3558. Min Act: -0.0000

Data Index: 435574 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.3762. Min Act: -0.0000

Data Index: 576924 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.3314. Min Act: -0.0000

Data Index: 570558 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1297065 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.3102. Min Act: -0.0000

Data Index: 876204 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2977. Min Act: 0.0000

Data Index: 445635 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2917. Min Act: -0.0001

Data Index: 15153 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2914. Min Act: -0.0000

Data Index: 795677 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2857. Min Act: -0.0000

Data Index: 876463 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2884. Min Act: -0.0000

Data Index: 410998 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2853. Min Act: -0.0000

Data Index: 857374 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2810. Min Act: 0.0000

Data Index: 1357002 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1115907 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2819. Min Act: -0.0001

Data Index: 501141 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2638. Min Act: 0.0001

Data Index: 473961 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1147196 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2654. Min Act: -0.0000

Data Index: 774489 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.5048. Min Range: -0.5048

Max Act: 0.2554. Min Act: -0.0001

Data Index: 262141 (C4 (Web Text))

Max Activating Token Index: 399