Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.9549. Min Act: -0.0001

Data Index: 219476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7558. Min Act: -0.0000

Data Index: 111842 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7559. Min Act: -0.0001

Data Index: 8603 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7810. Min Act: -0.0000

Data Index: 691592 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8009. Min Act: -0.0001

Data Index: 184507 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1194672 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1428655 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1336006 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7757. Min Act: -0.0001

Data Index: 994891 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7813. Min Act: -0.0001

Data Index: 280968 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7895. Min Act: -0.0000

Data Index: 956572 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7517. Min Act: -0.0001

Data Index: 552911 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1534087 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6868. Min Act: -0.0001

Data Index: 1417856 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6874. Min Act: -0.0000

Data Index: 467218 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6107. Min Act: -0.0000

Data Index: 757419 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1272240 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1518602 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1592986 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.5932. Min Act: -0.0001

Data Index: 182111 (C4 (Web Text))

Max Activating Token Index: 964