Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 189 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0001

Data Index: 168550 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1265565 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3050. Min Act: -0.0001

Data Index: 265621 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3042. Min Act: -0.0001

Data Index: 282207 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1223717 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2891. Min Act: -0.0001

Data Index: 821085 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2858. Min Act: -0.0001

Data Index: 121705 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1299870 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1256974 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2933. Min Act: -0.0001

Data Index: 395569 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2822. Min Act: -0.0001

Data Index: 176493 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2925. Min Act: -0.0001

Data Index: 367056 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2553. Min Act: -0.0001

Data Index: 818538 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2717. Min Act: -0.0001

Data Index: 230322 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1235735 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1339256 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2853. Min Act: -0.0001

Data Index: 3952 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2774. Min Act: -0.0001

Data Index: 845530 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2755. Min Act: -0.0001

Data Index: 202073 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2659. Min Act: -0.0001

Data Index: 794731 (C4 (Web Text))

Max Activating Token Index: 711