Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.7142. Min Act: -0.0000

Data Index: 370237 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.3898. Min Act: -0.0000

Data Index: 1146060 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.5886. Min Act: -0.0000

Data Index: 210188 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.2891. Min Act: -0.0000

Data Index: 838782 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.3362. Min Act: -0.0000

Data Index: 720897 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.1594. Min Act: -0.0000

Data Index: 844866 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.2983. Min Act: -0.0001

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.8828. Min Act: -0.0000

Data Index: 495899 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.1910. Min Act: -0.0000

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.9577. Min Act: -0.0000

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.9381. Min Act: -0.0000

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.7124. Min Act: -0.0000

Data Index: 508793 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.0999. Min Act: -0.0000

Data Index: 917051 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1166404 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.9062. Min Act: -0.0000

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.7142. Min Range: -2.7142

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1297753 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.8223. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.7565. Min Act: -0.0000

Data Index: 447830 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.7974. Min Act: -0.0000

Data Index: 424738 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 2.7142. Min Range: -2.7142

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1298338 (C4 (Web Text))

Max Activating Token Index: 349