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

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

Neuron 3011 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9257. Min Range: -5.9257

Max Act: 5.7495. Min Act: -0.0001

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 5.9257. Min Range: -5.9257

Max Act: 5.9257. Min Act: -0.0001

Data Index: 1060106 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.9257. Min Range: -5.9257

Max Act: 5.3783. Min Act: -0.0001

Data Index: 363278 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.9366. Min Act: -0.0001

Data Index: 678442 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.7571. Min Act: -0.0001

Data Index: 106361 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.7191. Min Act: -0.0001

Data Index: 686305 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.0001. Min Act: -0.0001

Data Index: 1006991 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.6087. Min Act: -0.0001

Data Index: 48707 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.9168. Min Act: -0.0001

Data Index: 13034 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.3457. Min Act: -0.0001

Data Index: 489064 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.0030. Min Act: -0.0001

Data Index: 1151797 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.8664. Min Act: -0.0001

Data Index: 61077 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.0127. Min Act: -0.0001

Data Index: 921490 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 5.9257. Min Range: -5.9257

Max Act: 4.1872. Min Act: -0.0001

Data Index: 204805 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.8199. Min Act: -0.0001

Data Index: 525486 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.9739. Min Act: -0.0001

Data Index: 1087739 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.6285. Min Act: -0.0001

Data Index: 35155 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.6096. Min Act: -0.0001

Data Index: 12011 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.4495. Min Act: -0.0001

Data Index: 717548 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 5.9257. Min Range: -5.9257

Max Act: 3.5865. Min Act: -0.0001

Data Index: 439408 (C4 (Web Text))

Max Activating Token Index: 506