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

Dataset: The Pile

Neuron 1603 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1485. Min Act: -0.0000

Data Index: 938187 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1940305 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1424. Min Act: -0.0000

Data Index: 534152 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1472. Min Act: -0.0000

Data Index: 880620 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1335. Min Act: -0.0000

Data Index: 741516 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1130665 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1297565 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1369. Min Act: -0.0000

Data Index: 924667 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1336. Min Act: -0.0000

Data Index: 386442 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1346. Min Act: 0.0000

Data Index: 1975391 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1012233 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1209. Min Act: 0.0000

Data Index: 671701 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1606420 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1240. Min Act: -0.0000

Data Index: 595091 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1079170 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1139. Min Act: -0.0000

Data Index: 565585 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1052550 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1450004 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1128. Min Act: 0.0000

Data Index: 26305 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 0.1488. Min Range: -0.1488

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1626690 (The Pile)

Max Activating Token Index: 98