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

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

Neuron 2935 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 668921 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1156278 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1116753 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2749. Min Act: -0.0000

Data Index: 355936 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2730. Min Act: -0.0000

Data Index: 632467 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1257744 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2647. Min Act: -0.0000

Data Index: 107956 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1759 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2684. Min Act: -0.0000

Data Index: 514745 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2703. Min Act: -0.0000

Data Index: 727969 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2321. Min Act: -0.0000

Data Index: 399396 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1052012 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1179579 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1079480 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2521. Min Act: -0.0000

Data Index: 889692 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1499016 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2502. Min Act: -0.0000

Data Index: 898480 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1039423 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2412. Min Act: -0.0000

Data Index: 232575 (C4 (Web Text))

Max Activating Token Index: 531