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

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

Neuron 1415 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: 0.3524. Min Range: -0.3524

Max Act: 0.3284. Min Act: -0.0000

Data Index: 373750 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3384. Min Act: -0.0001

Data Index: 1005021 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3524. Min Act: -0.0001

Data Index: 564452 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3289. Min Act: -0.0000

Data Index: 613801 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3385. Min Act: -0.0000

Data Index: 600405 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3149. Min Act: -0.0001

Data Index: 665268 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3152. Min Act: -0.0000

Data Index: 238743 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3241. Min Act: -0.0001

Data Index: 883912 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3117. Min Act: -0.0001

Data Index: 826522 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3096. Min Act: -0.0001

Data Index: 201601 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3081. Min Act: -0.0000

Data Index: 189451 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1055247 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3044. Min Act: -0.0001

Data Index: 730147 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1027752 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3097. Min Act: -0.0000

Data Index: 757516 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3101. Min Act: -0.0001

Data Index: 320147 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2907. Min Act: -0.0001

Data Index: 41819 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1053630 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2969. Min Act: -0.0000

Data Index: 294288 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2740. Min Act: -0.0000

Data Index: 895327 (C4 (Web Text))

Max Activating Token Index: 158