Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1112 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3646. Min Act: -0.0001

Data Index: 828660 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3614. Min Act: -0.0001

Data Index: 431284 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3373. Min Act: -0.0001

Data Index: 281150 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3457. Min Act: -0.0001

Data Index: 1132464 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3251. Min Act: -0.0001

Data Index: 526027 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3107. Min Act: -0.0001

Data Index: 56267 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2947. Min Act: -0.0001

Data Index: 535928 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1291378 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3044. Min Act: -0.0001

Data Index: 223428 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3018. Min Act: -0.0001

Data Index: 956076 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2890. Min Act: -0.0001

Data Index: 26039 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1114326 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1246695 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2907. Min Act: -0.0001

Data Index: 106728 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2872. Min Act: -0.0001

Data Index: 558584 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2984. Min Act: -0.0001

Data Index: 290833 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2871. Min Act: -0.0001

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2816. Min Act: -0.0001

Data Index: 567417 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2828. Min Act: -0.0001

Data Index: 897426 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2494. Min Act: -0.0001

Data Index: 583635 (C4 (Web Text))

Max Activating Token Index: 662