Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4962 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.6081. Min Act: 0.0001

Data Index: 1227788 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.2533. Min Act: 0.0000

Data Index: 614426 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.2327. Min Act: -0.0000

Data Index: 615821 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1978. Min Act: -0.0000

Data Index: 913354 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1800. Min Act: -0.0000

Data Index: 49481 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1749. Min Act: -0.0000

Data Index: 1039889 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.2482. Min Act: 0.0000

Data Index: 364939 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1349. Min Act: 0.0000

Data Index: 1268500 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1160. Min Act: 0.0000

Data Index: 430979 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1102. Min Act: -0.0000

Data Index: 176680 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.0988. Min Act: 0.0000

Data Index: 486907 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.0764. Min Act: 0.0001

Data Index: 1111011 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1943. Min Act: 0.0000

Data Index: 799223 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.0601. Min Act: 0.0000

Data Index: 902257 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.1736. Min Act: 0.0000

Data Index: 735863 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.6081. Min Range: -2.6081

Max Act: 1.9969. Min Act: 0.0000

Data Index: 1100908 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 2.6081. Min Range: -2.6081

Max Act: 1.9479. Min Act: -0.0000

Data Index: 217320 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.6081. Min Range: -2.6081

Max Act: 1.9620. Min Act: -0.0000

Data Index: 418245 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 2.6081. Min Range: -2.6081

Max Act: 1.9143. Min Act: -0.0000

Data Index: 767116 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.0050. Min Act: -0.0000

Data Index: 1038764 (C4 (Web Text))

Max Activating Token Index: 637