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

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

Neuron 4802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1567922 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1386237 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1637958 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1455419 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1636514 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1517364 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1568303 (Python Code)

Max Activating Token Index: 977

Text #7

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1494708 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1530386 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1599343 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1424479 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1567928 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1500791 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1377857 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1525042 (Python Code)

Max Activating Token Index: 489

Text #15

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1609695 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1615536 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1632549 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1538430 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1424255 (Python Code)

Max Activating Token Index: 389