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

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

Neuron 2452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.6051. Min Act: -0.0001

Data Index: 960111 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.5898. Min Act: -0.0001

Data Index: 588484 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.5694. Min Act: -0.0001

Data Index: 592462 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4895. Min Act: -0.0001

Data Index: 182451 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4503. Min Act: -0.0001

Data Index: 686440 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4677. Min Act: -0.0001

Data Index: 362052 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4490. Min Act: -0.0001

Data Index: 263735 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4479. Min Act: -0.0001

Data Index: 853107 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1037286 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4113. Min Act: -0.0001

Data Index: 301312 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4471. Min Act: -0.0001

Data Index: 935860 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.3933. Min Act: -0.0001

Data Index: 33592 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4326. Min Act: -0.0001

Data Index: 941527 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4063. Min Act: -0.0001

Data Index: 419993 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4232. Min Act: -0.0001

Data Index: 933195 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4762. Min Act: -0.0001

Data Index: 879922 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4022. Min Act: -0.0001

Data Index: 110646 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1173849 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.3858. Min Act: -0.0001

Data Index: 702169 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.6051. Min Range: -0.6051

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1007612 (C4 (Web Text))

Max Activating Token Index: 57