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

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

Neuron 4492 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.4352. Min Act: -0.0000

Data Index: 1547232 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.2043. Min Act: -0.0000

Data Index: 1443527 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.2824. Min Act: -0.0000

Data Index: 519140 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.1830. Min Act: -0.0000

Data Index: 1573119 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.2654. Min Act: -0.0000

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.1087. Min Act: -0.0000

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.2524. Min Act: -0.0000

Data Index: 445789 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0167. Min Act: -0.0000

Data Index: 1447489 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0167. Min Act: -0.0000

Data Index: 1379344 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0827. Min Act: -0.0000

Data Index: 1464437 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0289. Min Act: -0.0000

Data Index: 1632051 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1506106 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.9952. Min Act: -0.0000

Data Index: 457899 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1361095 (Python Code)

Max Activating Token Index: 592

Text #14

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1596981 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.9277. Min Act: -0.0000

Data Index: 1288241 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.0197. Min Act: -0.0000

Data Index: 392591 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1458622 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 2.4352. Min Range: -2.4352

Max Act: 1.9995. Min Act: -0.0000

Data Index: 1493937 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 2.4352. Min Range: -2.4352

Max Act: 2.1145. Min Act: -0.0000

Data Index: 489227 (C4 (Web Text))

Max Activating Token Index: 214