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

Dataset: The Pile

Neuron 281 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0000

Data Index: 994990 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0469. Min Act: -0.0000

Data Index: 633046 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1424455 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0398. Min Act: -0.0000

Data Index: 237236 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1704533 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1409390 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1156495 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0390. Min Act: -0.0000

Data Index: 749951 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0369. Min Act: -0.0000

Data Index: 75633 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1755544 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0331. Min Act: -0.0000

Data Index: 305505 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1041552 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1650704 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0340. Min Act: -0.0000

Data Index: 685114 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0355. Min Act: -0.0000

Data Index: 251660 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1569423 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0339. Min Act: -0.0000

Data Index: 874482 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0322. Min Act: -0.0000

Data Index: 620758 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0332. Min Act: -0.0000

Data Index: 329888 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1511845 (The Pile)

Max Activating Token Index: 49