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

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

Neuron 5715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4977. Min Range: -2.4977

Max Act: 2.4977. Min Act: -0.0000

Data Index: 464555 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.4977. Min Range: -2.4977

Max Act: 2.0242. Min Act: -0.0000

Data Index: 756335 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.9203. Min Act: -0.0000

Data Index: 373592 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.6986. Min Act: -0.0000

Data Index: 315621 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.7487. Min Act: -0.0000

Data Index: 631566 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1214268 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4342. Min Act: -0.0000

Data Index: 13745 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5736. Min Act: -0.0000

Data Index: 820400 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1146730 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5042. Min Act: -0.0000

Data Index: 64473 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1057832 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4941. Min Act: -0.0000

Data Index: 312325 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4881. Min Act: -0.0000

Data Index: 957793 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1010628 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.2897. Min Act: -0.0000

Data Index: 693134 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1130502 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.4088. Min Act: -0.0000

Data Index: 27678 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.3821. Min Act: -0.0000

Data Index: 995057 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.4977. Min Range: -2.4977

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1349826 (C4 (Web Text))

Max Activating Token Index: 302