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

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

Neuron 3896 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3615. Min Act: -0.0003

Data Index: 479157 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3660. Min Act: -0.0003

Data Index: 500836 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3522. Min Act: -0.0003

Data Index: 412061 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3471. Min Act: -0.0003

Data Index: 1152383 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3342. Min Act: -0.0003

Data Index: 1266666 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3116. Min Act: -0.0003

Data Index: 680330 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3176. Min Act: -0.0003

Data Index: 345300 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3070. Min Act: -0.0003

Data Index: 1338476 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3112. Min Act: -0.0003

Data Index: 263274 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3091. Min Act: -0.0003

Data Index: 606532 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3080. Min Act: -0.0002

Data Index: 1108022 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2931. Min Act: -0.0003

Data Index: 983266 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2926. Min Act: -0.0003

Data Index: 866792 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2906. Min Act: -0.0003

Data Index: 1230816 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2996. Min Act: -0.0003

Data Index: 535109 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2887. Min Act: -0.0003

Data Index: 396710 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3091. Min Act: -0.0003

Data Index: 280915 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2872. Min Act: -0.0003

Data Index: 1251327 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2973. Min Act: -0.0003

Data Index: 1353381 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3058. Min Act: -0.0003

Data Index: 630956 (C4 (Web Text))

Max Activating Token Index: 17