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

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

Neuron 311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1106858 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0992. Min Act: -0.0002

Data Index: 382317 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0979. Min Act: -0.0002

Data Index: 339626 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0975. Min Act: -0.0002

Data Index: 610602 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0961. Min Act: -0.0002

Data Index: 886886 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0937. Min Act: -0.0002

Data Index: 104755 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1094083 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0926. Min Act: -0.0002

Data Index: 154753 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0920. Min Act: -0.0002

Data Index: 304084 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0906. Min Act: -0.0002

Data Index: 539064 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0901. Min Act: -0.0002

Data Index: 402801 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0916. Min Act: -0.0002

Data Index: 648270 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0887. Min Act: -0.0002

Data Index: 11855 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0890. Min Act: -0.0002

Data Index: 762469 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1191505 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0877. Min Act: -0.0002

Data Index: 418978 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0884. Min Act: -0.0002

Data Index: 543251 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1330530 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0875. Min Act: -0.0002

Data Index: 439684 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0874. Min Act: -0.0002

Data Index: 820288 (C4 (Web Text))

Max Activating Token Index: 754