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

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

Neuron 3227 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: 1.1970. Min Range: -1.1970

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1386601 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 1.1970. Min Range: -1.1970

Max Act: 1.1970. Min Act: 0.0000

Data Index: 1311963 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.1970. Min Range: -1.1970

Max Act: 1.0583. Min Act: -0.0000

Data Index: 886341 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.1970. Min Range: -1.1970

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1496705 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1318965 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7916. Min Act: -0.0000

Data Index: 339223 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.8797. Min Act: 0.0000

Data Index: 791623 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1431157 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7413. Min Act: -0.0000

Data Index: 603204 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1608439 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1465743 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1435626 (Python Code)

Max Activating Token Index: 943

Text #13

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1318704 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1641040 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1116890 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6599. Min Act: -0.0000

Data Index: 124267 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6315. Min Act: -0.0000

Data Index: 220723 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6444. Min Act: -0.0000

Data Index: 603899 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.1970. Min Range: -1.1970

Max Act: 0.6472. Min Act: -0.0000

Data Index: 790366 (C4 (Web Text))

Max Activating Token Index: 302