Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2509 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1577245 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1631107 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1584441 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1617692 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1382424 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1506146 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1605341 (Python Code)

Max Activating Token Index: 805

Text #7

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1453326 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1589957 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6238. Min Act: -0.0001

Data Index: 1470069 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5995. Min Act: -0.0001

Data Index: 1521659 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6143. Min Act: -0.0001

Data Index: 1648416 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1386943 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1521866 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5851. Min Act: -0.0001

Data Index: 1563322 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1375048 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1652656 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1518588 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1387032 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1361525 (Python Code)

Max Activating Token Index: 42