Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.8155. Min Act: -0.0001

Data Index: 270146 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.7788. Min Act: -0.0001

Data Index: 558159 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.7307. Min Act: -0.0001

Data Index: 893309 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5593. Min Act: -0.0001

Data Index: 514910 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3813. Min Act: -0.0001

Data Index: 1013594 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5255. Min Act: -0.0001

Data Index: 139367 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.6527. Min Act: -0.0001

Data Index: 701919 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5837. Min Act: -0.0001

Data Index: 865051 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5486. Min Act: -0.0001

Data Index: 81047 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5401. Min Act: -0.0001

Data Index: 763288 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5493. Min Act: -0.0001

Data Index: 276267 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3764. Min Act: -0.0001

Data Index: 755958 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.2993. Min Act: -0.0001

Data Index: 654012 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.5342. Min Act: -0.0001

Data Index: 1227700 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.2479. Min Act: -0.0001

Data Index: 877696 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3907. Min Act: -0.0001

Data Index: 756998 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.2395. Min Act: -0.0001

Data Index: 891208 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3792. Min Act: -0.0001

Data Index: 349778 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3821. Min Act: -0.0001

Data Index: 944280 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 3.8155. Min Range: -3.8155

Max Act: 3.3712. Min Act: -0.0001

Data Index: 1121646 (C4 (Web Text))

Max Activating Token Index: 720