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

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

Neuron 2680 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1387194 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1626681 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1605583 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1609970 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1582853 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1521473 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1444257 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1465414 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1599419 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1383665 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1573346 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1510451 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1415265 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1513497 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1535571 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1407518 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1453966 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1459663 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1567896 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1595684 (Python Code)

Max Activating Token Index: 19