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

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

Neuron 1966 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6703. Min Act: -0.0001

Data Index: 229350 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5223. Min Act: -0.0001

Data Index: 1068351 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5697. Min Act: -0.0001

Data Index: 1257593 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1332401 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5382. Min Act: -0.0001

Data Index: 114663 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5114. Min Act: -0.0001

Data Index: 930229 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5329. Min Act: -0.0001

Data Index: 498295 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5367. Min Act: -0.0001

Data Index: 1078469 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4990. Min Act: -0.0001

Data Index: 498914 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4965. Min Act: -0.0001

Data Index: 383520 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1000883 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4917. Min Act: -0.0001

Data Index: 157346 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4962. Min Act: -0.0001

Data Index: 1202167 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4689. Min Act: -0.0001

Data Index: 1343931 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4424. Min Act: -0.0001

Data Index: 472327 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4082. Min Act: -0.0001

Data Index: 2482 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4432. Min Act: -0.0001

Data Index: 189408 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3947. Min Act: -0.0001

Data Index: 782187 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4066. Min Act: -0.0001

Data Index: 587189 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3773. Min Act: -0.0001

Data Index: 389804 (C4 (Web Text))

Max Activating Token Index: 523