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

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

Neuron 3713 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: 0.4537. Min Range: -0.4537

Max Act: 0.4537. Min Act: -0.0001

Data Index: 479484 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3225. Min Act: -0.0001

Data Index: 31421 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3217. Min Act: -0.0001

Data Index: 839109 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2826. Min Act: -0.0001

Data Index: 833635 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2911. Min Act: -0.0001

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3071. Min Act: -0.0001

Data Index: 794814 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3136. Min Act: -0.0001

Data Index: 714363 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2809. Min Act: -0.0001

Data Index: 347969 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2779. Min Act: -0.0001

Data Index: 334646 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1193692 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2808. Min Act: -0.0001

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1111441 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2684. Min Act: -0.0001

Data Index: 746108 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2686. Min Act: -0.0000

Data Index: 436231 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2683. Min Act: -0.0001

Data Index: 269097 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2849. Min Act: -0.0000

Data Index: 320107 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2939. Min Act: -0.0001

Data Index: 819713 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1331240 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2706. Min Act: -0.0001

Data Index: 208449 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1211016 (C4 (Web Text))

Max Activating Token Index: 370