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

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

Neuron 2388 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.2953. Min Act: -0.0000

Data Index: 697301 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.2162. Min Act: -0.0000

Data Index: 293836 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1963. Min Act: -0.0000

Data Index: 467361 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1930. Min Act: -0.0000

Data Index: 562858 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.2147. Min Act: -0.0000

Data Index: 251729 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1212. Min Act: -0.0000

Data Index: 778050 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1945. Min Act: -0.0000

Data Index: 865111 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0956. Min Act: -0.0000

Data Index: 657758 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1045848 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0478. Min Act: -0.0000

Data Index: 252924 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0479. Min Act: -0.0000

Data Index: 589092 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0766. Min Act: -0.0000

Data Index: 789669 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1134527 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1332319 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0128. Min Act: -0.0000

Data Index: 891058 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0872. Min Act: -0.0000

Data Index: 743861 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0414. Min Act: -0.0000

Data Index: 75535 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9979. Min Act: -0.0000

Data Index: 847038 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0243. Min Act: -0.0000

Data Index: 691479 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0634. Min Act: -0.0000

Data Index: 886780 (C4 (Web Text))

Max Activating Token Index: 840