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

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

Neuron 1306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.4894. Min Act: -0.0001

Data Index: 551400 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3614. Min Act: -0.0001

Data Index: 1263674 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3339. Min Act: -0.0001

Data Index: 482755 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3312. Min Act: -0.0001

Data Index: 885214 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3020. Min Act: -0.0001

Data Index: 970108 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1219897 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2741. Min Act: -0.0001

Data Index: 361534 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3033. Min Act: -0.0001

Data Index: 327113 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1085778 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3028. Min Act: -0.0001

Data Index: 915089 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1270944 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1119153 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2908. Min Act: -0.0001

Data Index: 1192872 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3089. Min Act: -0.0001

Data Index: 380035 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2911. Min Act: -0.0001

Data Index: 904866 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2783. Min Act: -0.0001

Data Index: 428929 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1291949 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2775. Min Act: -0.0001

Data Index: 838892 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2952. Min Act: -0.0001

Data Index: 608145 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.2755. Min Act: -0.0001

Data Index: 705336 (C4 (Web Text))

Max Activating Token Index: 908