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

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

Neuron 2707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5432. Min Act: -0.0001

Data Index: 1655652 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1367577 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3874. Min Act: -0.0001

Data Index: 1397207 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1580269 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3937. Min Act: -0.0001

Data Index: 1395931 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3791. Min Act: -0.0001

Data Index: 1513444 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1527361 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1396420 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1396157 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1576012 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1570677 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1645817 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3357. Min Act: -0.0001

Data Index: 1366905 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3243. Min Act: -0.0001

Data Index: 1368108 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3310. Min Act: -0.0001

Data Index: 1436534 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3291. Min Act: -0.0001

Data Index: 1394806 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1482996 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1551503 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3202. Min Act: -0.0001

Data Index: 1565616 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3343. Min Act: -0.0001

Data Index: 1476526 (Python Code)

Max Activating Token Index: 663