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

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

Neuron 2846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.3175. Min Act: -0.0001

Data Index: 197628 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.3101. Min Act: -0.0001

Data Index: 775480 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2972. Min Act: -0.0001

Data Index: 943473 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1024032 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2939. Min Act: -0.0001

Data Index: 752095 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2842. Min Act: -0.0000

Data Index: 289206 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2891. Min Act: -0.0001

Data Index: 644364 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2784. Min Act: -0.0001

Data Index: 982680 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2904. Min Act: -0.0000

Data Index: 415053 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2875. Min Act: -0.0001

Data Index: 657027 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1266617 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2764. Min Act: -0.0001

Data Index: 483985 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1014908 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2662. Min Act: -0.0001

Data Index: 741847 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2684. Min Act: -0.0001

Data Index: 313148 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2637. Min Act: -0.0001

Data Index: 502447 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2953. Min Act: -0.0001

Data Index: 914595 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2805. Min Act: -0.0001

Data Index: 884027 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2709. Min Act: -0.0001

Data Index: 786665 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2777. Min Act: -0.0001

Data Index: 728600 (C4 (Web Text))

Max Activating Token Index: 662