Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3060 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.3043. Min Act: -0.0002

Data Index: 976160 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.3048. Min Act: -0.0002

Data Index: 419643 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2997. Min Act: -0.0002

Data Index: 1291862 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2972. Min Act: -0.0002

Data Index: 55836 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2894. Min Act: -0.0002

Data Index: 488195 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2969. Min Act: -0.0002

Data Index: 118287 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2938. Min Act: -0.0002

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2831. Min Act: -0.0002

Data Index: 6941 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2820. Min Act: -0.0002

Data Index: 1150940 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2855. Min Act: -0.0002

Data Index: 495592 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2724. Min Act: -0.0002

Data Index: 364144 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2788. Min Act: -0.0002

Data Index: 1096482 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2740. Min Act: -0.0002

Data Index: 1289385 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2617. Min Act: -0.0002

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2610. Min Act: -0.0002

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2640. Min Act: -0.0002

Data Index: 1031724 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2461. Min Act: -0.0002

Data Index: 413540 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2521. Min Act: -0.0002

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2429. Min Act: -0.0002

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2512. Min Act: -0.0002

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 564