Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0001

Data Index: 684325 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0457. Min Act: -0.0001

Data Index: 222542 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1008862 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1292 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1264062 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0390. Min Act: -0.0001

Data Index: 792266 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0432. Min Act: -0.0000

Data Index: 783020 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0392. Min Act: -0.0000

Data Index: 104884 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0405. Min Act: -0.0001

Data Index: 360810 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0402. Min Act: -0.0000

Data Index: 645561 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0398. Min Act: -0.0000

Data Index: 7786 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0395. Min Act: -0.0001

Data Index: 957001 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0371. Min Act: -0.0001

Data Index: 719615 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0371. Min Act: -0.0001

Data Index: 140291 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0369. Min Act: -0.0000

Data Index: 998289 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1333826 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0383. Min Act: -0.0001

Data Index: 136441 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1100457 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0349. Min Act: -0.0000

Data Index: 199883 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0331. Min Act: -0.0000

Data Index: 982658 (C4 (Web Text))

Max Activating Token Index: 177