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

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

Neuron 5164 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: 3.9933. Min Range: -3.9933

Max Act: 3.9933. Min Act: -0.0000

Data Index: 1624540 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.9127. Min Act: -0.0000

Data Index: 1372274 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6148. Min Act: -0.0000

Data Index: 1402500 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1467113 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.1410. Min Act: -0.0000

Data Index: 1579395 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.4320. Min Act: -0.0000

Data Index: 1387856 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.9912. Min Act: -0.0000

Data Index: 1431254 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.1410. Min Act: -0.0000

Data Index: 730319 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.9610. Min Act: -0.0000

Data Index: 1571057 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1626579 (Python Code)

Max Activating Token Index: 848

Text #10

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.1783. Min Act: -0.0000

Data Index: 1453385 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.7157. Min Act: -0.0000

Data Index: 468380 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1602087 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.5316. Min Act: -0.0000

Data Index: 1330344 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.8931. Min Act: -0.0000

Data Index: 1526280 (Python Code)

Max Activating Token Index: 477

Text #15

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.2381. Min Act: -0.0000

Data Index: 733418 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.8825. Min Act: -0.0000

Data Index: 623248 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.0060. Min Act: -0.0000

Data Index: 375928 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.5455. Min Act: -0.0000

Data Index: 1569502 (Python Code)

Max Activating Token Index: 757

Text #19

Max Range: 3.9933. Min Range: -3.9933

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1455472 (Python Code)

Max Activating Token Index: 151