Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 621 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1206227 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1263657 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1066054 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 114596 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 999605 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0006

Data Index: 149606 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 592940 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 643620 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 744228 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 422530 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 167071 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 864649 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1031898 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1191268 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 72755 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 264956 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 112636 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 439601 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 892026 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 86304 (C4 (Web Text))

Max Activating Token Index: 1000