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

Dataset: The Pile

Neuron 4858 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.6241. Min Act: -0.0000

Data Index: 1093062 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4131. Min Act: -0.0000

Data Index: 989500 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1893. Min Act: -0.0000

Data Index: 585319 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1315. Min Act: -0.0000

Data Index: 807155 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1989251 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1124. Min Act: -0.0000

Data Index: 560431 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.2449. Min Act: -0.0000

Data Index: 58300 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.2151. Min Act: -0.0000

Data Index: 196062 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.3248. Min Act: -0.0000

Data Index: 1587446 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.0238. Min Act: -0.0000

Data Index: 217621 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1559. Min Act: -0.0000

Data Index: 1248714 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1476. Min Act: -0.0000

Data Index: 1324915 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 3.6241. Min Range: -3.6241

Max Act: 2.9694. Min Act: -0.0000

Data Index: 617826 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1171. Min Act: -0.0000

Data Index: 1196578 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.0988. Min Act: -0.0000

Data Index: 1095920 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.0805. Min Act: -0.0000

Data Index: 145429 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.2242. Min Act: -0.0000

Data Index: 1371189 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.1605. Min Act: -0.0000

Data Index: 657691 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 3.6241. Min Range: -3.6241

Max Act: 2.8789. Min Act: -0.0000

Data Index: 212382 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.0070. Min Act: -0.0000

Data Index: 1664376 (The Pile)

Max Activating Token Index: 93