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

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

Neuron 5893 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.8236. Min Act: -0.0002

Data Index: 201168 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.6972. Min Act: -0.0002

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.7106. Min Act: -0.0002

Data Index: 1311193 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.7121. Min Act: -0.0002

Data Index: 517246 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5794. Min Act: -0.0002

Data Index: 212960 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5869. Min Act: -0.0002

Data Index: 784339 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.6494. Min Act: -0.0002

Data Index: 1124877 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5716. Min Act: -0.0002

Data Index: 849707 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5345. Min Act: -0.0002

Data Index: 86116 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5166. Min Act: -0.0002

Data Index: 487523 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5236. Min Act: -0.0002

Data Index: 91516 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4963. Min Act: -0.0002

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5646. Min Act: -0.0002

Data Index: 356887 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4570. Min Act: -0.0002

Data Index: 1090851 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4776. Min Act: -0.0002

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4225. Min Act: -0.0002

Data Index: 448221 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4816. Min Act: -0.0002

Data Index: 1139769 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.5324. Min Act: -0.0002

Data Index: 1131369 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4365. Min Act: -0.0002

Data Index: 273997 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 2.8236. Min Range: -2.8236

Max Act: 2.4550. Min Act: -0.0002

Data Index: 21698 (C4 (Web Text))

Max Activating Token Index: 712