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

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

Neuron 256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.3152. Min Act: -0.0000

Data Index: 7713 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1012285 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2917. Min Act: -0.0000

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2550. Min Act: -0.0000

Data Index: 597406 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1335264 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1111947 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2445. Min Act: -0.0001

Data Index: 310132 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2584. Min Act: -0.0000

Data Index: 711773 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2496. Min Act: -0.0001

Data Index: 931696 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2492. Min Act: -0.0001

Data Index: 257152 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2688. Min Act: -0.0001

Data Index: 158479 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2759. Min Act: -0.0001

Data Index: 632203 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2416. Min Act: -0.0000

Data Index: 646236 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2504. Min Act: -0.0001

Data Index: 304050 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2180. Min Act: -0.0001

Data Index: 890765 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2487. Min Act: -0.0001

Data Index: 123356 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1140328 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.1937. Min Act: -0.0000

Data Index: 483743 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2687. Min Act: -0.0000

Data Index: 727421 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.1967. Min Act: -0.0001

Data Index: 486261 (C4 (Web Text))

Max Activating Token Index: 902