Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 400 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1569623 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0318. Min Act: -0.0005

Data Index: 1490433 (Python Code)

Max Activating Token Index: 479

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0302. Min Act: -0.0005

Data Index: 745000 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0300. Min Act: -0.0005

Data Index: 1494804 (Python Code)

Max Activating Token Index: 973

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0296. Min Act: -0.0005

Data Index: 1617970 (Python Code)

Max Activating Token Index: 731

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0293. Min Act: -0.0005

Data Index: 1593251 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1441371 (Python Code)

Max Activating Token Index: 532

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1532560 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1547917 (Python Code)

Max Activating Token Index: 953

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1556428 (Python Code)

Max Activating Token Index: 654

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1376919 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0284. Min Act: -0.0005

Data Index: 121826 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1407262 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1482679 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1441620 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1450875 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1474018 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0005

Data Index: 202064 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0004

Data Index: 95802 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0270. Min Act: -0.0005

Data Index: 1051821 (C4 (Web Text))

Max Activating Token Index: 867