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

Dataset: The Pile

Neuron 4640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1519184 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1391. Min Act: -0.0000

Data Index: 616106 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1420. Min Act: -0.0000

Data Index: 969259 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1244. Min Act: -0.0000

Data Index: 709217 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1177. Min Act: -0.0000

Data Index: 247591 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1300. Min Act: -0.0000

Data Index: 525870 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1209. Min Act: -0.0000

Data Index: 700818 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1574795 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1269262 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1177. Min Act: -0.0000

Data Index: 964018 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1201 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1171. Min Act: -0.0000

Data Index: 401595 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1249480 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1110. Min Act: -0.0000

Data Index: 127877 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1742486 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1192. Min Act: -0.0000

Data Index: 64645 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1093. Min Act: -0.0000

Data Index: 884959 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1267653 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1127. Min Act: -0.0000

Data Index: 798046 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1793826 (The Pile)

Max Activating Token Index: 520