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

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

Neuron 690 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: 0.1021. Min Range: -0.1021

Max Act: 0.0982. Min Act: -0.0001

Data Index: 892640 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 237721 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0983. Min Act: -0.0001

Data Index: 113983 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1044500 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1265976 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0934. Min Act: -0.0001

Data Index: 263033 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0973. Min Act: -0.0001

Data Index: 171160 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1304490 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1122539 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0956. Min Act: -0.0001

Data Index: 82372 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1236702 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1327451 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0988. Min Act: -0.0001

Data Index: 147870 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0888. Min Act: -0.0001

Data Index: 164518 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0935. Min Act: -0.0001

Data Index: 858642 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0907. Min Act: -0.0001

Data Index: 337842 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0961. Min Act: -0.0001

Data Index: 756871 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0897. Min Act: -0.0001

Data Index: 951740 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0930. Min Act: -0.0001

Data Index: 939233 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1230742 (C4 (Web Text))

Max Activating Token Index: 606