Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5106 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4987. Min Act: -0.0000

Data Index: 139290 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.5312. Min Act: -0.0000

Data Index: 330694 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.5041. Min Act: -0.0000

Data Index: 899277 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1352166 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4865. Min Act: -0.0000

Data Index: 95210 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4811. Min Act: -0.0000

Data Index: 543591 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1249774 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1274301 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4473. Min Act: -0.0000

Data Index: 759490 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4147. Min Act: -0.0000

Data Index: 328697 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1291469 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4256. Min Act: -0.0000

Data Index: 538593 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4068. Min Act: -0.0000

Data Index: 233989 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3947. Min Act: -0.0000

Data Index: 750310 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3903. Min Act: -0.0000

Data Index: 768581 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3816. Min Act: -0.0000

Data Index: 936726 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1256116 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3587. Min Act: -0.0000

Data Index: 643318 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3501. Min Act: -0.0000

Data Index: 790115 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3596. Min Act: -0.0000

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 914