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

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

Neuron 1587 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6450. Min Act: -0.0004

Data Index: 5865 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6431. Min Act: -0.0004

Data Index: 82740 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5986. Min Act: -0.0004

Data Index: 1186072 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6326. Min Act: -0.0004

Data Index: 666071 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5862. Min Act: -0.0004

Data Index: 383870 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6189. Min Act: -0.0004

Data Index: 699102 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5152. Min Act: -0.0004

Data Index: 561153 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5908. Min Act: -0.0004

Data Index: 99515 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.6207. Min Act: -0.0004

Data Index: 1000916 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.4904. Min Act: -0.0004

Data Index: 337821 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5937. Min Act: -0.0004

Data Index: 1023453 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5898. Min Act: -0.0004

Data Index: 820212 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5893. Min Act: -0.0004

Data Index: 772059 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5444. Min Act: -0.0004

Data Index: 150074 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5828. Min Act: -0.0004

Data Index: 945949 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5642. Min Act: -0.0004

Data Index: 1213105 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5642. Min Act: -0.0004

Data Index: 24713 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5527. Min Act: -0.0004

Data Index: 240194 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5265. Min Act: -0.0004

Data Index: 598727 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.6450. Min Range: -0.6450

Max Act: 0.5671. Min Act: -0.0004

Data Index: 629871 (C4 (Web Text))

Max Activating Token Index: 13