Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1505527 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1379484 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1636028 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1402979 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1600189 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1465038 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1364234 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1368416 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1645261 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1370468 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1606360 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1555878 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1604473 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1378390 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1566540 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1425923 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1505653 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1651942 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1549231 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1477004 (Python Code)

Max Activating Token Index: 21