Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.9444. Min Act: -0.0003

Data Index: 81792 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.9722. Min Act: -0.0003

Data Index: 538365 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.0083. Min Range: -1.0083

Max Act: 1.0083. Min Act: -0.0003

Data Index: 1238274 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8784. Min Act: -0.0003

Data Index: 930095 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.9714. Min Act: -0.0003

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7567. Min Act: -0.0003

Data Index: 227530 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7985. Min Act: -0.0003

Data Index: 1127444 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8906. Min Act: -0.0003

Data Index: 731039 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.6986. Min Act: -0.0003

Data Index: 465671 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8801. Min Act: -0.0003

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8767. Min Act: -0.0003

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8452. Min Act: -0.0003

Data Index: 1345520 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8381. Min Act: -0.0003

Data Index: 209206 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8093. Min Act: -0.0003

Data Index: 842584 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8419. Min Act: -0.0003

Data Index: 146950 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7977. Min Act: -0.0003

Data Index: 790657 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7963. Min Act: -0.0003

Data Index: 1173701 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7245. Min Act: -0.0003

Data Index: 856895 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.7886. Min Act: -0.0003

Data Index: 1241620 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.0083. Min Range: -1.0083

Max Act: 0.8666. Min Act: -0.0003

Data Index: 1106215 (C4 (Web Text))

Max Activating Token Index: 280