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

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

Neuron 4610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2884. Min Act: -0.0000

Data Index: 324174 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2534. Min Act: -0.0000

Data Index: 244105 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2433. Min Act: -0.0000

Data Index: 903577 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2351. Min Act: -0.0000

Data Index: 477029 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2495. Min Act: -0.0000

Data Index: 983891 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2582. Min Act: -0.0000

Data Index: 166979 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2363. Min Act: -0.0000

Data Index: 540766 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2457. Min Act: -0.0000

Data Index: 884205 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2274. Min Act: -0.0000

Data Index: 631915 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2226. Min Act: -0.0000

Data Index: 596732 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2138. Min Act: -0.0000

Data Index: 236936 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1987. Min Act: -0.0000

Data Index: 141395 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1840. Min Act: -0.0000

Data Index: 526280 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1985. Min Act: -0.0000

Data Index: 639410 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1157964 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1796. Min Act: -0.0000

Data Index: 558358 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1323759 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1562. Min Act: -0.0000

Data Index: 844620 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1460. Min Act: -0.0000

Data Index: 471484 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.1408. Min Act: -0.0000

Data Index: 927791 (C4 (Web Text))

Max Activating Token Index: 670