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

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

Neuron 1145 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.3564. Min Act: -0.0000

Data Index: 1360550 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.5963. Min Act: -0.0000

Data Index: 1537108 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.1044. Min Act: -0.0000

Data Index: 1549252 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.0976. Min Act: -0.0000

Data Index: 1582950 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.3470. Min Act: -0.0000

Data Index: 1555559 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.3574. Min Act: -0.0000

Data Index: 1479297 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.9728. Min Act: -0.0000

Data Index: 1459780 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.8931. Min Act: -0.0000

Data Index: 1580662 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.2315. Min Act: -0.0000

Data Index: 1403231 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.2225. Min Act: -0.0000

Data Index: 1572709 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.3044. Min Act: -0.0000

Data Index: 1567094 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.6157. Min Act: -0.0000

Data Index: 1457422 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.9395. Min Act: -0.0000

Data Index: 1562340 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.8540. Min Act: -0.0000

Data Index: 1556938 (Python Code)

Max Activating Token Index: 833

Text #14

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.5330. Min Act: -0.0000

Data Index: 1655718 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.6261. Min Act: -0.0000

Data Index: 1582515 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.7907. Min Act: -0.0000

Data Index: 1609537 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.7583. Min Act: -0.0000

Data Index: 1427518 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.7477. Min Act: -0.0000

Data Index: 1412297 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 5.3564. Min Range: -5.3564

Max Act: 3.3776. Min Act: -0.0000

Data Index: 1420020 (Python Code)

Max Activating Token Index: 564