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

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

Neuron 2717 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4621. Min Act: -0.0001

Data Index: 949211 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4459. Min Act: -0.0001

Data Index: 431486 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4438. Min Act: -0.0001

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1142422 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4080. Min Act: -0.0001

Data Index: 921499 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1310888 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3878. Min Act: -0.0001

Data Index: 684298 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3749. Min Act: -0.0001

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3858. Min Act: -0.0001

Data Index: 1302662 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3840. Min Act: -0.0001

Data Index: 156898 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3950. Min Act: -0.0001

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3935. Min Act: -0.0001

Data Index: 230198 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3897. Min Act: -0.0001

Data Index: 273286 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3754. Min Act: -0.0001

Data Index: 74060 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3623. Min Act: -0.0001

Data Index: 679348 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3599. Min Act: -0.0001

Data Index: 831941 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1202995 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1239619 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3354. Min Act: -0.0001

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3606. Min Act: -0.0001

Data Index: 785784 (C4 (Web Text))

Max Activating Token Index: 49