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

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

Neuron 1617 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: 5.6297. Min Range: -5.6297

Max Act: 5.5332. Min Act: -0.0000

Data Index: 226761 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.5431. Min Act: -0.0000

Data Index: 569107 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.6297. Min Act: -0.0000

Data Index: 572451 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.1844. Min Act: -0.0000

Data Index: 1069841 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.9561. Min Act: -0.0000

Data Index: 388264 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.1297. Min Act: -0.0000

Data Index: 723620 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.0874. Min Act: -0.0000

Data Index: 1177110 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.9728. Min Act: -0.0000

Data Index: 946956 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.8036. Min Act: -0.0000

Data Index: 835967 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.1585. Min Act: -0.0000

Data Index: 1117540 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.9569. Min Act: -0.0000

Data Index: 513871 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.7462. Min Act: -0.0000

Data Index: 981989 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.9312. Min Act: -0.0000

Data Index: 658152 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.5752. Min Act: -0.0000

Data Index: 302300 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 5.6297. Min Range: -5.6297

Max Act: 5.3302. Min Act: -0.0000

Data Index: 293063 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.7055. Min Act: -0.0000

Data Index: 1001567 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.8138. Min Act: -0.0000

Data Index: 795973 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.7886. Min Act: -0.0000

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.5787. Min Act: -0.0000

Data Index: 416665 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 5.6297. Min Range: -5.6297

Max Act: 4.7599. Min Act: -0.0000

Data Index: 1084303 (C4 (Web Text))

Max Activating Token Index: 490