Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.8114. Min Act: -0.0000

Data Index: 24378 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.7278. Min Act: -0.0000

Data Index: 512139 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.7765. Min Act: -0.0000

Data Index: 228763 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1454 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6874. Min Act: -0.0000

Data Index: 246025 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6510. Min Act: -0.0000

Data Index: 439320 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6903. Min Act: -0.0000

Data Index: 46124 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1199779 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1251996 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5943. Min Act: -0.0000

Data Index: 671077 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5938. Min Act: -0.0000

Data Index: 114958 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1037016 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6181. Min Act: -0.0000

Data Index: 332765 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6753. Min Act: -0.0000

Data Index: 902138 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6323. Min Act: -0.0000

Data Index: 985167 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5862. Min Act: -0.0000

Data Index: 140881 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6272. Min Act: -0.0000

Data Index: 768870 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5968. Min Act: -0.0000

Data Index: 849635 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5969. Min Act: -0.0000

Data Index: 127791 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1243830 (C4 (Web Text))

Max Activating Token Index: 485