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

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

Neuron 1730 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: 1.0774. Min Range: -1.0774

Max Act: 1.0774. Min Act: -0.0002

Data Index: 720178 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.0774. Min Range: -1.0774

Max Act: 1.0462. Min Act: -0.0002

Data Index: 233488 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.0774. Min Range: -1.0774

Max Act: 1.0249. Min Act: -0.0002

Data Index: 79591 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.0774. Min Range: -1.0774

Max Act: 1.0069. Min Act: -0.0003

Data Index: 965938 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.0774. Min Range: -1.0774

Max Act: 1.0030. Min Act: -0.0002

Data Index: 284727 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.0774. Min Range: -1.0774

Max Act: 1.0010. Min Act: -0.0002

Data Index: 412635 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9827. Min Act: -0.0002

Data Index: 94670 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9705. Min Act: -0.0002

Data Index: 1211579 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9669. Min Act: -0.0002

Data Index: 1349545 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9425. Min Act: -0.0002

Data Index: 774588 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9227. Min Act: -0.0002

Data Index: 1070748 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9437. Min Act: -0.0002

Data Index: 738157 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9250. Min Act: -0.0002

Data Index: 588926 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9379. Min Act: -0.0002

Data Index: 1262627 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9147. Min Act: -0.0002

Data Index: 706423 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9174. Min Act: -0.0002

Data Index: 1239833 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9059. Min Act: -0.0002

Data Index: 681283 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9147. Min Act: -0.0002

Data Index: 884111 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9224. Min Act: -0.0002

Data Index: 253832 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.0774. Min Range: -1.0774

Max Act: 0.9043. Min Act: -0.0002

Data Index: 491850 (C4 (Web Text))

Max Activating Token Index: 40