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

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

Neuron 1402 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0942. Min Act: -0.0001

Data Index: 342757 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0410. Min Act: -0.0001

Data Index: 487459 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1571603 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9802. Min Act: -0.0001

Data Index: 371931 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1259108 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7411. Min Act: -0.0001

Data Index: 1295458 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7416. Min Act: -0.0001

Data Index: 936481 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7568. Min Act: -0.0001

Data Index: 243117 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7861. Min Act: -0.0001

Data Index: 279758 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7686. Min Act: -0.0001

Data Index: 493792 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7806. Min Act: -0.0001

Data Index: 1549976 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7784. Min Act: -0.0001

Data Index: 59882 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7328. Min Act: -0.0001

Data Index: 443293 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7081. Min Act: -0.0001

Data Index: 176207 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7741. Min Act: -0.0001

Data Index: 712750 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7040. Min Act: -0.0001

Data Index: 277048 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7436. Min Act: -0.0001

Data Index: 645393 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.6958. Min Act: -0.0001

Data Index: 767365 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.7245. Min Act: -0.0001

Data Index: 436690 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.6141. Min Act: -0.0001

Data Index: 1034265 (C4 (Web Text))

Max Activating Token Index: 982