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

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

Neuron 4525 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3875. Min Range: -1.3875

Max Act: 1.3875. Min Act: -0.0002

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.3875. Min Range: -1.3875

Max Act: 1.1775. Min Act: -0.0002

Data Index: 1282525 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.3875. Min Range: -1.3875

Max Act: 1.0330. Min Act: -0.0002

Data Index: 400444 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.3875. Min Range: -1.3875

Max Act: 1.0142. Min Act: -0.0002

Data Index: 92363 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9756. Min Act: -0.0002

Data Index: 319276 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9709. Min Act: -0.0002

Data Index: 817993 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9578. Min Act: -0.0002

Data Index: 294171 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9478. Min Act: -0.0002

Data Index: 1102114 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9324. Min Act: -0.0002

Data Index: 136746 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9322. Min Act: -0.0002

Data Index: 831944 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9476. Min Act: -0.0002

Data Index: 651654 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9134. Min Act: -0.0002

Data Index: 303128 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9244. Min Act: -0.0002

Data Index: 496731 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9103. Min Act: -0.0003

Data Index: 746865 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.9136. Min Act: -0.0002

Data Index: 58161 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.8948. Min Act: -0.0002

Data Index: 385803 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.8710. Min Act: -0.0002

Data Index: 548634 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.8848. Min Act: -0.0002

Data Index: 1349079 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.8956. Min Act: -0.0002

Data Index: 1293238 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.3875. Min Range: -1.3875

Max Act: 0.8815. Min Act: -0.0002

Data Index: 146443 (C4 (Web Text))

Max Activating Token Index: 684