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

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

Neuron 4303 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: 0.4305. Min Range: -0.4305

Max Act: 0.4305. Min Act: -0.0000

Data Index: 461081 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.4064. Min Act: -0.0000

Data Index: 769021 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.4040. Min Act: -0.0000

Data Index: 676057 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1120628 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3489. Min Act: -0.0000

Data Index: 885108 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1185066 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3337. Min Act: -0.0000

Data Index: 440809 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1085693 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3228. Min Act: -0.0000

Data Index: 128779 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2914. Min Act: -0.0000

Data Index: 951697 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2966. Min Act: -0.0000

Data Index: 589482 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3199. Min Act: -0.0000

Data Index: 718680 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2951. Min Act: -0.0000

Data Index: 169472 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3229. Min Act: -0.0000

Data Index: 855274 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3386. Min Act: -0.0000

Data Index: 693023 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3115. Min Act: -0.0000

Data Index: 61072 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3022. Min Act: -0.0000

Data Index: 785010 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2771. Min Act: -0.0000

Data Index: 934610 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2924. Min Act: -0.0000

Data Index: 663798 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3103. Min Act: -0.0000

Data Index: 121228 (C4 (Web Text))

Max Activating Token Index: 633