Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2889 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1335215 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.2033. Min Act: -0.0000

Data Index: 33412 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9103. Min Act: -0.0000

Data Index: 784160 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7895. Min Act: -0.0000

Data Index: 92073 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1329944 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1339264 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7176. Min Act: -0.0000

Data Index: 953176 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1186885 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6541. Min Act: -0.0000

Data Index: 297597 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1144066 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1056020 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6330. Min Act: -0.0000

Data Index: 462233 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6093. Min Act: -0.0000

Data Index: 889716 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6223. Min Act: -0.0000

Data Index: 282630 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1046504 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6269. Min Act: -0.0000

Data Index: 374580 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.5782. Min Act: -0.0000

Data Index: 220668 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6123. Min Act: -0.0000

Data Index: 24903 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6512. Min Act: -0.0000

Data Index: 692782 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.6127. Min Act: -0.0000

Data Index: 745561 (C4 (Web Text))

Max Activating Token Index: 723