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

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

Neuron 2696 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1081097 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4348. Min Act: -0.0000

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1044916 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3647. Min Act: -0.0000

Data Index: 385297 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1070940 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2867. Min Act: -0.0000

Data Index: 188032 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3158. Min Act: -0.0000

Data Index: 416894 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3118. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3421. Min Act: -0.0000

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3309. Min Act: -0.0000

Data Index: 309394 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3046. Min Act: -0.0000

Data Index: 366780 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3076. Min Act: -0.0000

Data Index: 642254 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2908. Min Act: -0.0000

Data Index: 18988 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1269298 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3298. Min Act: -0.0000

Data Index: 372324 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1197787 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2986. Min Act: -0.0000

Data Index: 98123 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2909. Min Act: -0.0000

Data Index: 781157 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2651. Min Act: -0.0000

Data Index: 51540 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.2944. Min Act: -0.0000

Data Index: 148633 (C4 (Web Text))

Max Activating Token Index: 1019