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

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

Neuron 1358 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: 1.9547. Min Range: -1.9547

Max Act: 1.9171. Min Act: -0.0001

Data Index: 1506450 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1376152 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.9268. Min Act: -0.0001

Data Index: 1567124 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1467643 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.8293. Min Act: -0.0001

Data Index: 766392 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.7974. Min Act: -0.0001

Data Index: 1579065 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1507933 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1385604 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6095. Min Act: -0.0001

Data Index: 532409 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1471996 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1467520 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1422176 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5654. Min Act: -0.0001

Data Index: 1635803 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.4747. Min Act: -0.0001

Data Index: 1557958 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5722. Min Act: -0.0001

Data Index: 1570835 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.3898. Min Act: -0.0001

Data Index: 1188790 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1630065 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5409. Min Act: -0.0001

Data Index: 1602979 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6326. Min Act: -0.0001

Data Index: 1520783 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1373727 (Python Code)

Max Activating Token Index: 332