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

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

Neuron 4723 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: 0.8269. Min Range: -0.8269

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1389396 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1488373 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1553366 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1459661 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1365394 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1464969 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1533003 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1482744 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1499489 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1523292 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1394244 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1386444 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1656970 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1476964 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1425626 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1644323 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1402547 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1368709 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1605993 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1606693 (Python Code)

Max Activating Token Index: 767