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

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

Neuron 442 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1375071 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1554128 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4101. Min Act: -0.0000

Data Index: 361773 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1163362 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1375878 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1322888 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1003155 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3713. Min Act: -0.0000

Data Index: 463040 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.2939. Min Act: -0.0000

Data Index: 345989 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3352. Min Act: -0.0000

Data Index: 79537 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1415481 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1514107 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3054. Min Act: -0.0000

Data Index: 617278 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3157. Min Act: -0.0000

Data Index: 283025 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1613936 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.2903. Min Act: -0.0000

Data Index: 583647 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1443138 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1123335 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3010. Min Act: 0.0003

Data Index: 1139244 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1232324 (C4 (Web Text))

Max Activating Token Index: 80