Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 205 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2492. Min Act: -0.0001

Data Index: 291707 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2349. Min Act: -0.0001

Data Index: 263833 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2346. Min Act: -0.0001

Data Index: 994204 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2475. Min Act: -0.0001

Data Index: 439713 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1065748 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1941. Min Act: -0.0001

Data Index: 799924 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1887. Min Act: -0.0001

Data Index: 539662 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1693. Min Act: -0.0001

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1143442 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1178290 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1947. Min Act: -0.0001

Data Index: 169300 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1501. Min Act: -0.0001

Data Index: 950414 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1187708 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1289301 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1817. Min Act: -0.0001

Data Index: 112954 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1100096 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1173222 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1476. Min Act: -0.0001

Data Index: 703360 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1134437 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1765. Min Act: -0.0001

Data Index: 302051 (C4 (Web Text))

Max Activating Token Index: 664