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

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

Neuron 5928 in Layer 0

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: 0.5181. Min Range: -0.5181

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1084904 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4817. Min Act: -0.0001

Data Index: 79658 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4667. Min Act: -0.0001

Data Index: 26653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4537. Min Act: -0.0001

Data Index: 601145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4546. Min Act: -0.0001

Data Index: 1016162 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1325523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4519. Min Act: -0.0001

Data Index: 369443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4429. Min Act: -0.0001

Data Index: 736458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4388. Min Act: -0.0001

Data Index: 1255029 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1270529 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4328. Min Act: -0.0001

Data Index: 552360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1031550 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1003300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4268. Min Act: -0.0001

Data Index: 573591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4123. Min Act: -0.0001

Data Index: 804785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4175. Min Act: -0.0001

Data Index: 366348 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4185. Min Act: -0.0001

Data Index: 1213797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1034898 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4101. Min Act: -0.0001

Data Index: 866473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4038. Min Act: -0.0001

Data Index: 1167484 (C4 (Web Text))

Max Activating Token Index: 27