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

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

Neuron 2770 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: 0.5653. Min Range: -0.5653

Max Act: 0.5653. Min Act: 0.0002

Data Index: 1159089 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1208831 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4927. Min Act: -0.0001

Data Index: 81259 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1207517 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1114620 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4947. Min Act: -0.0001

Data Index: 856587 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4777. Min Act: -0.0001

Data Index: 452407 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4487. Min Act: -0.0001

Data Index: 968948 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4543. Min Act: -0.0001

Data Index: 323144 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4376. Min Act: -0.0001

Data Index: 976870 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4581. Min Act: -0.0001

Data Index: 289731 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1329136 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4665. Min Act: -0.0001

Data Index: 561304 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4489. Min Act: 0.0001

Data Index: 178070 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4424. Min Act: -0.0000

Data Index: 638794 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4418. Min Act: 0.0002

Data Index: 584077 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4252. Min Act: -0.0001

Data Index: 1083119 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4251. Min Act: -0.0001

Data Index: 152499 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4498. Min Act: -0.0001

Data Index: 638277 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.5653. Min Range: -0.5653

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1133779 (C4 (Web Text))

Max Activating Token Index: 329