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

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

Neuron 4259 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: 0.2081. Min Range: -0.2081

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1429755 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1589789 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1510556 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1585732 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1562835 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1383598 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1555647 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1435068 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1596361 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1439119 (Python Code)

Max Activating Token Index: 92

Text #10

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1472108 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1472292 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1508555 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1451532 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1608174 (Python Code)

Max Activating Token Index: 707

Text #15

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1481840 (Python Code)

Max Activating Token Index: 904

Text #16

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1389151 (Python Code)

Max Activating Token Index: 471

Text #17

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1439296 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1481774 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1379056 (Python Code)

Max Activating Token Index: 642