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

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

Neuron 844 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: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0006

Data Index: 366625 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0076. Min Act: -0.0006

Data Index: 394924 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0077. Min Act: -0.0006

Data Index: 543176 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0072. Min Act: -0.0006

Data Index: 144854 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0072. Min Act: -0.0006

Data Index: 448365 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1103897 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0071. Min Act: -0.0006

Data Index: 829690 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0070. Min Act: -0.0006

Data Index: 658065 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0069. Min Act: -0.0006

Data Index: 744800 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0066. Min Act: -0.0006

Data Index: 761778 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0068. Min Act: -0.0006

Data Index: 90887 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0069. Min Act: -0.0006

Data Index: 801240 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1221167 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0064. Min Act: -0.0006

Data Index: 85569 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0065. Min Act: -0.0006

Data Index: 517224 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1168774 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0061. Min Act: -0.0006

Data Index: 137959 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1128192 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0062. Min Act: -0.0006

Data Index: 135006 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0061. Min Act: -0.0006

Data Index: 275273 (C4 (Web Text))

Max Activating Token Index: 769