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

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

Neuron 1174 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2076. Min Range: -2.2076

Max Act: 2.1753. Min Act: -0.0000

Data Index: 27487 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 2.2076. Min Range: -2.2076

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1020583 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 2.2076. Min Range: -2.2076

Max Act: 2.1757. Min Act: -0.0000

Data Index: 250069 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 2.2076. Min Range: -2.2076

Max Act: 2.1007. Min Act: -0.0000

Data Index: 235609 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.9797. Min Act: -0.0000

Data Index: 209609 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.8938. Min Act: -0.0000

Data Index: 560556 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1161166 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.9515. Min Act: -0.0000

Data Index: 247043 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.8293. Min Act: -0.0000

Data Index: 587363 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1137555 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.9287. Min Act: -0.0000

Data Index: 389858 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7847. Min Act: -0.0000

Data Index: 1246702 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1342614 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7760. Min Act: -0.0000

Data Index: 1084814 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.6585. Min Act: -0.0000

Data Index: 630347 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7347. Min Act: -0.0000

Data Index: 818909 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7229. Min Act: 0.0000

Data Index: 313375 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.6052. Min Act: -0.0000

Data Index: 710262 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.6134. Min Act: -0.0000

Data Index: 62785 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.2076. Min Range: -2.2076

Max Act: 1.7001. Min Act: -0.0000

Data Index: 485089 (C4 (Web Text))

Max Activating Token Index: 489