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

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

Neuron 2786 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3651. Min Act: -0.0001

Data Index: 790888 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3424. Min Act: -0.0001

Data Index: 391876 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3155. Min Act: -0.0001

Data Index: 611880 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3115. Min Act: -0.0001

Data Index: 955190 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3092. Min Act: -0.0001

Data Index: 713821 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3057. Min Act: -0.0001

Data Index: 1039433 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3031. Min Act: -0.0001

Data Index: 275210 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1147702 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3064. Min Act: -0.0001

Data Index: 586822 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2921. Min Act: -0.0001

Data Index: 363634 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2986. Min Act: -0.0001

Data Index: 628360 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2978. Min Act: -0.0001

Data Index: 658494 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2730. Min Act: -0.0001

Data Index: 713485 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1354396 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2875. Min Act: -0.0001

Data Index: 277193 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1079682 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2947. Min Act: -0.0001

Data Index: 325677 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2822. Min Act: -0.0001

Data Index: 319612 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2833. Min Act: -0.0001

Data Index: 876128 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.2811. Min Act: -0.0001

Data Index: 500141 (C4 (Web Text))

Max Activating Token Index: 853