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

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

Neuron 3678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2277. Min Range: -1.2277

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1491928 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 1.2277. Min Range: -1.2277

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1402513 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1462912 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1427220 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1639195 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1605881 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1455674 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1411335 (Python Code)

Max Activating Token Index: 403

Text #8

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1636107 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1512799 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1629019 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1483614 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1486036 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1595531 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1559254 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1648384 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1635430 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1579002 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1635971 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1387593 (Python Code)

Max Activating Token Index: 537