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

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

Neuron 4626 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: 1.8418. Min Range: -1.8418

Max Act: 1.8418. Min Act: -0.0001

Data Index: 611471 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5593. Min Act: -0.0001

Data Index: 429925 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.7512. Min Act: -0.0001

Data Index: 1032764 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5644. Min Act: -0.0001

Data Index: 258019 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.6484. Min Act: -0.0001

Data Index: 1123226 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5189. Min Act: -0.0001

Data Index: 511940 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5049. Min Act: -0.0001

Data Index: 792332 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5652. Min Act: -0.0001

Data Index: 586152 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4781. Min Act: -0.0001

Data Index: 340652 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5361. Min Act: -0.0001

Data Index: 1166305 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5193. Min Act: -0.0001

Data Index: 327373 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4377. Min Act: -0.0001

Data Index: 399029 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.5110. Min Act: -0.0001

Data Index: 610711 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4239. Min Act: -0.0001

Data Index: 963279 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.3611. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4089. Min Act: -0.0001

Data Index: 52981 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4684. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.4054. Min Act: -0.0001

Data Index: 469654 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.2384. Min Act: -0.0001

Data Index: 1005964 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.8418. Min Range: -1.8418

Max Act: 1.3063. Min Act: -0.0001

Data Index: 437640 (C4 (Web Text))

Max Activating Token Index: 861