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

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

Neuron 2510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4337. Min Act: -0.0001

Data Index: 882585 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3442. Min Act: -0.0000

Data Index: 701991 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3484. Min Act: -0.0001

Data Index: 380371 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3472. Min Act: -0.0001

Data Index: 650031 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1035714 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2936. Min Act: -0.0001

Data Index: 580089 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2983. Min Act: -0.0001

Data Index: 776516 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2857. Min Act: -0.0001

Data Index: 155278 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3152. Min Act: -0.0001

Data Index: 239340 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1154354 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3024. Min Act: -0.0001

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1239299 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2898. Min Act: -0.0000

Data Index: 789439 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2766. Min Act: -0.0001

Data Index: 331789 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3036. Min Act: -0.0001

Data Index: 370408 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3128. Min Act: -0.0000

Data Index: 199065 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1125554 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2753. Min Act: -0.0000

Data Index: 552045 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2759. Min Act: -0.0001

Data Index: 466748 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1042340 (C4 (Web Text))

Max Activating Token Index: 348