Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2966 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.6206. Min Act: -0.0001

Data Index: 395096 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5415. Min Act: -0.0000

Data Index: 850640 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5109. Min Act: -0.0001

Data Index: 619229 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4984. Min Act: -0.0000

Data Index: 147513 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4906. Min Act: 0.0000

Data Index: 731898 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5132. Min Act: -0.0001

Data Index: 392612 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4956. Min Act: -0.0001

Data Index: 804991 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4793. Min Act: 0.0002

Data Index: 912597 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4753. Min Act: -0.0001

Data Index: 135360 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4691. Min Act: -0.0001

Data Index: 320752 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4760. Min Act: -0.0001

Data Index: 1316694 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1285368 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4228. Min Act: -0.0000

Data Index: 259443 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4459. Min Act: -0.0001

Data Index: 985999 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4146. Min Act: -0.0001

Data Index: 151750 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4230. Min Act: 0.0000

Data Index: 966198 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1272257 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4363. Min Act: -0.0001

Data Index: 462808 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4117. Min Act: 0.0001

Data Index: 15734 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4089. Min Act: -0.0001

Data Index: 4506 (C4 (Web Text))

Max Activating Token Index: 562