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

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

Neuron 5581 in Layer 0

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: 0.7430. Min Range: -0.7430

Max Act: 0.7430. Min Act: -0.0001

Data Index: 720204 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.7281. Min Act: -0.0001

Data Index: 606639 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.7055. Min Act: -0.0001

Data Index: 529888 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6683. Min Act: -0.0001

Data Index: 418211 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6696. Min Act: -0.0001

Data Index: 280764 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6571. Min Act: -0.0001

Data Index: 827844 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6711. Min Act: -0.0001

Data Index: 754962 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6624. Min Act: -0.0001

Data Index: 139394 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6451. Min Act: -0.0001

Data Index: 76141 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6541. Min Act: -0.0001

Data Index: 238853 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6580. Min Act: -0.0001

Data Index: 1043879 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6593. Min Act: -0.0001

Data Index: 695947 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6465. Min Act: -0.0001

Data Index: 90293 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6517. Min Act: -0.0001

Data Index: 675425 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6551. Min Act: -0.0001

Data Index: 465073 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6398. Min Act: -0.0002

Data Index: 59370 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6592. Min Act: -0.0001

Data Index: 994652 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1343786 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6434. Min Act: -0.0001

Data Index: 994903 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6424. Min Act: -0.0001

Data Index: 1329651 (C4 (Web Text))

Max Activating Token Index: 221