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

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

Neuron 850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.8077. Min Act: -0.0003

Data Index: 1060301 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6904. Min Act: -0.0003

Data Index: 1151233 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6848. Min Act: -0.0003

Data Index: 713056 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5970. Min Act: -0.0003

Data Index: 903814 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6415. Min Act: -0.0003

Data Index: 656195 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5777. Min Act: -0.0003

Data Index: 563163 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6509. Min Act: -0.0003

Data Index: 710234 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6001. Min Act: -0.0003

Data Index: 113583 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.7206. Min Act: -0.0003

Data Index: 673983 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6427. Min Act: -0.0003

Data Index: 1000508 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5971. Min Act: -0.0003

Data Index: 1330156 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6145. Min Act: -0.0003

Data Index: 8877 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5927. Min Act: -0.0003

Data Index: 1181767 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5817. Min Act: -0.0003

Data Index: 1352559 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6471. Min Act: -0.0003

Data Index: 1317043 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6443. Min Act: -0.0003

Data Index: 340502 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5953. Min Act: -0.0003

Data Index: 1326672 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5904. Min Act: -0.0003

Data Index: 353514 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5911. Min Act: -0.0003

Data Index: 757614 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6039. Min Act: -0.0003

Data Index: 53349 (C4 (Web Text))

Max Activating Token Index: 868