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

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

Neuron 374 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6564. Min Act: -0.0004

Data Index: 827005 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0004

Data Index: 14312 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6045. Min Act: -0.0004

Data Index: 719442 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6665. Min Act: -0.0004

Data Index: 1112981 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5230. Min Act: -0.0004

Data Index: 24820 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6169. Min Act: -0.0004

Data Index: 1136137 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5575. Min Act: -0.0004

Data Index: 10026 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5749. Min Act: -0.0004

Data Index: 292312 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6747. Min Act: -0.0004

Data Index: 954511 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5311. Min Act: -0.0004

Data Index: 787782 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6463. Min Act: -0.0004

Data Index: 683261 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6175. Min Act: -0.0004

Data Index: 228778 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5875. Min Act: -0.0004

Data Index: 410384 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6215. Min Act: -0.0004

Data Index: 1119463 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6189. Min Act: -0.0004

Data Index: 476553 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4843. Min Act: -0.0004

Data Index: 1101993 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6090. Min Act: -0.0004

Data Index: 91852 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6081. Min Act: -0.0004

Data Index: 824584 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4988. Min Act: -0.0004

Data Index: 1144767 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5649. Min Act: -0.0004

Data Index: 128917 (C4 (Web Text))

Max Activating Token Index: 848