Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1118 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.9053. Min Act: -0.0001

Data Index: 1401808 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.6577. Min Act: -0.0000

Data Index: 1542751 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.5121. Min Act: -0.0001

Data Index: 1625506 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.7617. Min Act: -0.0000

Data Index: 1465488 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.8335. Min Act: -0.0000

Data Index: 1431642 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.5023. Min Act: -0.0000

Data Index: 1372694 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4827. Min Act: -0.0000

Data Index: 1470359 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4603. Min Act: -0.0001

Data Index: 1362185 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.2279. Min Act: -0.0000

Data Index: 1459083 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.5752. Min Act: -0.0001

Data Index: 1503299 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4412. Min Act: -0.0000

Data Index: 1606972 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4399. Min Act: -0.0000

Data Index: 1360883 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.5460. Min Act: -0.0000

Data Index: 1519737 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.2869. Min Act: -0.0000

Data Index: 1530148 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.5247. Min Act: -0.0000

Data Index: 1440883 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1460943 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4946. Min Act: -0.0000

Data Index: 1596401 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.3530. Min Act: -0.0000

Data Index: 1380237 (Python Code)

Max Activating Token Index: 486

Text #18

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4451. Min Act: -0.0000

Data Index: 1483289 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 2.9053. Min Range: -2.9053

Max Act: 2.4407. Min Act: -0.0000

Data Index: 1640526 (Python Code)

Max Activating Token Index: 491