Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3946. Min Act: -0.0000

Data Index: 550569 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.4123. Min Act: -0.0000

Data Index: 57297 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3721. Min Act: -0.0000

Data Index: 784903 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3551. Min Act: -0.0000

Data Index: 768881 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3554. Min Act: -0.0000

Data Index: 580817 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3524. Min Act: -0.0000

Data Index: 86653 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1048043 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3457. Min Act: -0.0000

Data Index: 208926 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3451. Min Act: -0.0000

Data Index: 60207 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3251. Min Act: -0.0000

Data Index: 669663 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3411. Min Act: -0.0000

Data Index: 573713 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3373. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3533. Min Act: -0.0000

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1344893 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3584. Min Act: -0.0000

Data Index: 92137 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3322. Min Act: -0.0000

Data Index: 366057 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1226025 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3168. Min Act: -0.0000

Data Index: 327816 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2972. Min Act: -0.0000

Data Index: 13548 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3083. Min Act: -0.0000

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 207