Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5964 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.7521. Min Act: -0.0001

Data Index: 276156 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5029. Min Act: -0.0001

Data Index: 599884 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5252. Min Act: -0.0001

Data Index: 1332184 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5702. Min Act: -0.0001

Data Index: 1205372 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.4417. Min Act: -0.0001

Data Index: 360157 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.4577. Min Act: -0.0001

Data Index: 194673 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3463. Min Act: -0.0001

Data Index: 506840 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.4628. Min Act: -0.0001

Data Index: 1092868 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3918. Min Act: -0.0001

Data Index: 1051960 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3694. Min Act: -0.0001

Data Index: 524179 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3733. Min Act: -0.0001

Data Index: 96706 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3681. Min Act: -0.0001

Data Index: 549472 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.1361. Min Act: -0.0001

Data Index: 862192 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.2823. Min Act: -0.0001

Data Index: 565423 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.1864. Min Act: -0.0001

Data Index: 430839 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.2030. Min Act: -0.0001

Data Index: 352246 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3418. Min Act: -0.0001

Data Index: 263961 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3374. Min Act: -0.0001

Data Index: 378885 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.3452. Min Act: -0.0001

Data Index: 508120 (C4 (Web Text))

Max Activating Token Index: 864