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

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

Neuron 676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0650. Min Act: -0.0002

Data Index: 875272 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0566. Min Act: -0.0002

Data Index: 759112 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0520. Min Act: -0.0002

Data Index: 276475 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1215231 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0467. Min Act: -0.0002

Data Index: 337149 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0479. Min Act: -0.0002

Data Index: 891810 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0456. Min Act: -0.0002

Data Index: 539414 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1218245 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0460. Min Act: -0.0002

Data Index: 304026 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0452. Min Act: -0.0002

Data Index: 692356 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1612634 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0444. Min Act: -0.0002

Data Index: 135036 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1620592 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0451. Min Act: -0.0002

Data Index: 772572 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0432. Min Act: -0.0002

Data Index: 745292 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1172789 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1158470 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1223389 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1485880 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0405. Min Act: -0.0002

Data Index: 700684 (C4 (Web Text))

Max Activating Token Index: 69