Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3030. Min Act: -0.0002

Data Index: 926421 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3114. Min Act: -0.0002

Data Index: 896819 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2770. Min Act: -0.0002

Data Index: 813056 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2937. Min Act: -0.0002

Data Index: 1323343 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3035. Min Act: -0.0002

Data Index: 509096 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2843. Min Act: -0.0002

Data Index: 130277 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2647. Min Act: -0.0002

Data Index: 15262 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2689. Min Act: -0.0002

Data Index: 142606 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2992. Min Act: -0.0002

Data Index: 1175738 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2551. Min Act: -0.0002

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2639. Min Act: -0.0002

Data Index: 573897 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2467. Min Act: -0.0002

Data Index: 1096683 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2607. Min Act: -0.0002

Data Index: 934532 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2435. Min Act: -0.0002

Data Index: 180429 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2516. Min Act: -0.0002

Data Index: 1271647 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2640. Min Act: -0.0002

Data Index: 500520 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2529. Min Act: -0.0002

Data Index: 158640 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2361. Min Act: -0.0002

Data Index: 958940 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2286. Min Act: -0.0002

Data Index: 156775 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2423. Min Act: -0.0002

Data Index: 988405 (C4 (Web Text))

Max Activating Token Index: 191