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

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

Neuron 4208 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.5150. Min Act: -0.0000

Data Index: 603515 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.1281. Min Act: -0.0000

Data Index: 143796 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.0907. Min Act: -0.0000

Data Index: 1099167 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.5150. Min Range: -3.5150

Max Act: 2.8015. Min Act: -0.0000

Data Index: 106056 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.5150. Min Range: -3.5150

Max Act: 2.1577. Min Act: 0.0000

Data Index: 1064991 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 3.5150. Min Range: -3.5150

Max Act: 2.2141. Min Act: 0.0000

Data Index: 306951 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.9607. Min Act: -0.0000

Data Index: 148483 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.5150. Min Range: -3.5150

Max Act: 2.0262. Min Act: -0.0000

Data Index: 471394 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.8534. Min Act: -0.0000

Data Index: 57378 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.8638. Min Act: -0.0000

Data Index: 469084 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1301346 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.9597. Min Act: -0.0000

Data Index: 663162 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7909. Min Act: -0.0000

Data Index: 895703 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7870. Min Act: 0.0000

Data Index: 981500 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7840. Min Act: 0.0000

Data Index: 839053 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7775. Min Act: -0.0000

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7331. Min Act: -0.0000

Data Index: 63550 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.7324. Min Act: -0.0000

Data Index: 589422 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.6587. Min Act: -0.0000

Data Index: 347169 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.5150. Min Range: -3.5150

Max Act: 1.6533. Min Act: -0.0000

Data Index: 293439 (C4 (Web Text))

Max Activating Token Index: 793