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

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

Neuron 2621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5717. Min Act: -0.0000

Data Index: 144047 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5395. Min Act: -0.0000

Data Index: 634885 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4539. Min Act: -0.0000

Data Index: 16776 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1102677 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4488. Min Act: -0.0000

Data Index: 117056 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1010502 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4269. Min Act: -0.0000

Data Index: 474183 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1223429 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3864. Min Act: -0.0000

Data Index: 439612 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4086. Min Act: -0.0000

Data Index: 417451 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3882. Min Act: -0.0000

Data Index: 222316 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3901. Min Act: -0.0000

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4030. Min Act: -0.0000

Data Index: 691276 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3962. Min Act: -0.0000

Data Index: 841799 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4053. Min Act: -0.0000

Data Index: 331200 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3890. Min Act: -0.0000

Data Index: 584555 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3991. Min Act: -0.0000

Data Index: 626426 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3869. Min Act: -0.0000

Data Index: 459029 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3949. Min Act: -0.0000

Data Index: 111267 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3802. Min Act: -0.0000

Data Index: 789974 (C4 (Web Text))

Max Activating Token Index: 289