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

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

Neuron 3689 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: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0002

Data Index: 43077 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0379. Min Act: -0.0003

Data Index: 121948 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0370. Min Act: -0.0002

Data Index: 739547 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1344528 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1010528 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0333. Min Act: -0.0002

Data Index: 832616 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0338. Min Act: -0.0002

Data Index: 445922 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0002

Data Index: 651675 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0327. Min Act: -0.0003

Data Index: 524142 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0322. Min Act: -0.0002

Data Index: 838649 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0319. Min Act: -0.0003

Data Index: 968247 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0314. Min Act: -0.0003

Data Index: 538747 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0316. Min Act: -0.0003

Data Index: 415216 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0311. Min Act: -0.0002

Data Index: 496923 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0310. Min Act: -0.0003

Data Index: 659997 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0307. Min Act: -0.0002

Data Index: 221179 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0301. Min Act: -0.0003

Data Index: 231560 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0305. Min Act: -0.0003

Data Index: 263607 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1083538 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1132269 (C4 (Web Text))

Max Activating Token Index: 73