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

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

Neuron 4375 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9537. Min Act: 0.0000

Data Index: 1551105 (Python Code)

Max Activating Token Index: 551

Text #1

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.4322. Min Act: -0.0000

Data Index: 1560111 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.1809. Min Act: -0.0000

Data Index: 1429520 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.2032. Min Act: -0.0000

Data Index: 1456138 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9143. Min Act: -0.0000

Data Index: 1368474 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9662. Min Act: -0.0000

Data Index: 1451935 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.6231. Min Act: -0.0000

Data Index: 548310 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.4475. Min Act: -0.0000

Data Index: 1453985 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.5570. Min Act: -0.0000

Data Index: 971140 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2435. Min Act: -0.0000

Data Index: 1395323 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2522. Min Act: -0.0000

Data Index: 845624 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.3051. Min Act: -0.0000

Data Index: 1394577 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2803. Min Act: -0.0000

Data Index: 1584540 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2897. Min Act: -0.0000

Data Index: 1635264 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.4092. Min Act: 0.0000

Data Index: 1628733 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 4.4322. Min Range: -4.4322

Max Act: 2.9741. Min Act: -0.0000

Data Index: 1590707 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2356. Min Act: -0.0000

Data Index: 1477858 (Python Code)

Max Activating Token Index: 706

Text #17

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2281. Min Act: -0.0000

Data Index: 1465771 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.2061. Min Act: -0.0000

Data Index: 118215 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.0771. Min Act: 0.0000

Data Index: 1563685 (Python Code)

Max Activating Token Index: 75