Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3913 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0001

Data Index: 538940 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1195548 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0555. Min Act: -0.0001

Data Index: 922338 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0531. Min Act: -0.0002

Data Index: 457469 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1350186 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0452. Min Act: -0.0001

Data Index: 392812 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0559. Min Act: -0.0002

Data Index: 654464 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1143625 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0552. Min Act: -0.0002

Data Index: 739717 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0524. Min Act: -0.0002

Data Index: 847130 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0507. Min Act: -0.0001

Data Index: 541427 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0504. Min Act: -0.0002

Data Index: 28920 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0499. Min Act: -0.0002

Data Index: 534217 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0578. Min Act: -0.0001

Data Index: 917103 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1109832 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0502. Min Act: -0.0002

Data Index: 908217 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0486. Min Act: -0.0002

Data Index: 889340 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0507. Min Act: -0.0002

Data Index: 993858 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1194745 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0484. Min Act: -0.0002

Data Index: 475334 (C4 (Web Text))

Max Activating Token Index: 674