Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.8547. Min Act: -0.0001

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5743. Min Act: -0.0001

Data Index: 460040 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.6215. Min Act: -0.0001

Data Index: 306776 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.6215. Min Act: -0.0001

Data Index: 792079 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5620. Min Act: -0.0001

Data Index: 105778 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5956. Min Act: -0.0001

Data Index: 90375 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5597. Min Act: -0.0001

Data Index: 147184 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5420. Min Act: -0.0001

Data Index: 442586 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5187. Min Act: -0.0001

Data Index: 1079251 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5096. Min Act: -0.0001

Data Index: 1174959 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5095. Min Act: -0.0001

Data Index: 114332 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.4718. Min Act: -0.0001

Data Index: 578639 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5050. Min Act: -0.0001

Data Index: 1852 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1358697 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5017. Min Act: -0.0001

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.4463. Min Act: -0.0001

Data Index: 638952 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.4935. Min Act: -0.0001

Data Index: 454816 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.4739. Min Act: -0.0001

Data Index: 621632 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.4874. Min Act: -0.0001

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.8547. Min Range: -0.8547

Max Act: 0.5064. Min Act: -0.0001

Data Index: 363763 (C4 (Web Text))

Max Activating Token Index: 400