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

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

Neuron 1618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3791. Min Act: -0.0000

Data Index: 682055 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4034. Min Act: -0.0000

Data Index: 768185 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3902. Min Act: -0.0000

Data Index: 650283 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3489. Min Act: -0.0000

Data Index: 43538 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1238318 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1202153 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3565. Min Act: -0.0000

Data Index: 568907 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4291. Min Act: -0.0000

Data Index: 731157 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3396. Min Act: -0.0000

Data Index: 74729 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3721. Min Act: -0.0000

Data Index: 301519 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1232622 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3399. Min Act: -0.0000

Data Index: 74089 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3309. Min Act: -0.0000

Data Index: 402225 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3194. Min Act: -0.0000

Data Index: 935706 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3237. Min Act: -0.0000

Data Index: 278379 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3131. Min Act: -0.0000

Data Index: 376460 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3286. Min Act: -0.0000

Data Index: 37673 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2987. Min Act: -0.0000

Data Index: 806949 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1011929 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3348. Min Act: -0.0000

Data Index: 958125 (C4 (Web Text))

Max Activating Token Index: 76