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

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

Neuron 705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3569. Min Act: -0.0001

Data Index: 528332 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3402. Min Act: -0.0001

Data Index: 663754 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3248. Min Act: -0.0001

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1104702 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3356. Min Act: -0.0001

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3080. Min Act: -0.0001

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3074. Min Act: -0.0001

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2994. Min Act: -0.0001

Data Index: 645676 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1327594 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2966. Min Act: -0.0001

Data Index: 560793 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2818. Min Act: -0.0001

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2917. Min Act: -0.0001

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3009. Min Act: -0.0001

Data Index: 950615 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1086331 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1179162 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2927. Min Act: -0.0001

Data Index: 486911 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1108513 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2693. Min Act: -0.0001

Data Index: 524964 (C4 (Web Text))

Max Activating Token Index: 431