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

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

Neuron 2625 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4918. Min Range: -3.4918

Max Act: 3.4918. Min Act: -0.0000

Data Index: 949307 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.4918. Min Range: -3.4918

Max Act: 3.3167. Min Act: -0.0000

Data Index: 266287 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.8232. Min Act: -0.0000

Data Index: 1171507 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 3.4918. Min Range: -3.4918

Max Act: 3.1183. Min Act: -0.0000

Data Index: 604394 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.8030. Min Act: -0.0000

Data Index: 715499 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.8901. Min Act: 0.0000

Data Index: 589881 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.7077. Min Act: -0.0000

Data Index: 469396 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.8092. Min Act: -0.0000

Data Index: 775409 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.6492. Min Act: -0.0000

Data Index: 220283 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.9259. Min Act: -0.0000

Data Index: 1352677 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.6055. Min Act: -0.0000

Data Index: 1048755 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.6985. Min Act: -0.0000

Data Index: 1195780 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.5861. Min Act: -0.0000

Data Index: 152707 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.6505. Min Act: -0.0000

Data Index: 459787 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.5239. Min Act: -0.0000

Data Index: 215356 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.5342. Min Act: -0.0000

Data Index: 619891 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.4942. Min Act: -0.0000

Data Index: 1161574 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1227455 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1163346 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 3.4918. Min Range: -3.4918

Max Act: 2.4948. Min Act: -0.0000

Data Index: 551494 (C4 (Web Text))

Max Activating Token Index: 255