Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3651 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.5401. Min Act: -0.0001

Data Index: 224021 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1242380 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3719. Min Act: -0.0001

Data Index: 1035078 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3526. Min Act: -0.0001

Data Index: 61921 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3504. Min Act: -0.0001

Data Index: 147854 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3131. Min Act: -0.0001

Data Index: 149211 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3251. Min Act: -0.0001

Data Index: 783837 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.3224. Min Act: -0.0001

Data Index: 520296 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1137875 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2704. Min Act: -0.0001

Data Index: 664338 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2943. Min Act: -0.0001

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2826. Min Act: -0.0001

Data Index: 87845 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1072952 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2808. Min Act: -0.0001

Data Index: 675962 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2620. Min Act: -0.0001

Data Index: 975565 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2573. Min Act: -0.0001

Data Index: 158525 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2784. Min Act: -0.0001

Data Index: 1092604 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2377. Min Act: -0.0001

Data Index: 80690 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2665. Min Act: -0.0001

Data Index: 966728 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.2615. Min Act: -0.0001

Data Index: 950436 (C4 (Web Text))

Max Activating Token Index: 818