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

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

Neuron 229 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: 0.3797. Min Range: -0.3797

Max Act: 0.3797. Min Act: -0.0001

Data Index: 712476 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3166. Min Act: -0.0001

Data Index: 927016 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3045. Min Act: -0.0001

Data Index: 219529 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2887. Min Act: -0.0001

Data Index: 815259 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1183655 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2809. Min Act: -0.0000

Data Index: 265866 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2892. Min Act: -0.0000

Data Index: 848110 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2736. Min Act: -0.0000

Data Index: 526876 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1321357 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2536. Min Act: -0.0000

Data Index: 691719 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2964. Min Act: -0.0001

Data Index: 1327844 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1329885 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1170859 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2470. Min Act: -0.0001

Data Index: 437883 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2799. Min Act: -0.0001

Data Index: 287455 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2334. Min Act: -0.0001

Data Index: 764660 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2373. Min Act: -0.0001

Data Index: 983644 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2387. Min Act: -0.0001

Data Index: 412625 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1143885 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2499. Min Act: -0.0001

Data Index: 587646 (C4 (Web Text))

Max Activating Token Index: 475