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

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

Neuron 3120 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0053. Min Range: -1.0053

Max Act: 1.0053. Min Act: -0.0001

Data Index: 1035378 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8875. Min Act: -0.0000

Data Index: 865720 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8822. Min Act: -0.0001

Data Index: 1166012 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8805. Min Act: -0.0001

Data Index: 779986 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8785. Min Act: -0.0000

Data Index: 151652 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1121229 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8967. Min Act: -0.0001

Data Index: 534750 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8303. Min Act: -0.0000

Data Index: 983377 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1073874 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7865. Min Act: -0.0000

Data Index: 559883 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8597. Min Act: -0.0000

Data Index: 957895 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1301089 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7360. Min Act: -0.0000

Data Index: 566689 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7038. Min Act: -0.0001

Data Index: 28851 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7559. Min Act: -0.0001

Data Index: 195937 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1322455 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7459. Min Act: -0.0000

Data Index: 524785 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7174. Min Act: -0.0000

Data Index: 702600 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7288. Min Act: -0.0001

Data Index: 900289 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7114. Min Act: -0.0001

Data Index: 709474 (C4 (Web Text))

Max Activating Token Index: 104