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

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

Neuron 2358 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3941. Min Act: -0.0000

Data Index: 101380 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3570. Min Act: -0.0000

Data Index: 261531 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3079. Min Act: -0.0000

Data Index: 992706 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2947. Min Act: -0.0000

Data Index: 749028 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1283078 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2945. Min Act: -0.0000

Data Index: 63490 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1547267 (Python Code)

Max Activating Token Index: 374

Text #7

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2549. Min Act: -0.0000

Data Index: 9275 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1103690 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2851. Min Act: -0.0000

Data Index: 269261 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1204105 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2682. Min Act: -0.0000

Data Index: 403801 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1012298 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1538816 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1591771 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1572168 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2640. Min Act: -0.0000

Data Index: 213964 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2686. Min Act: -0.0000

Data Index: 805289 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2671. Min Act: -0.0000

Data Index: 276985 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1594247 (Python Code)

Max Activating Token Index: 388