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

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

Neuron 1027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1291999 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1323756 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3682. Min Act: -0.0001

Data Index: 852909 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3939. Min Act: -0.0001

Data Index: 440809 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3908. Min Act: -0.0001

Data Index: 1085693 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3546. Min Act: -0.0001

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3173. Min Act: -0.0001

Data Index: 351723 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1085217 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3168. Min Act: -0.0001

Data Index: 489733 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3276. Min Act: -0.0001

Data Index: 814903 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1234938 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1045523 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3772. Min Act: -0.0001

Data Index: 925046 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3219. Min Act: -0.0001

Data Index: 1345951 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3481. Min Act: -0.0001

Data Index: 53845 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1129285 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3157. Min Act: -0.0001

Data Index: 65755 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3016. Min Act: -0.0001

Data Index: 386031 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.2933. Min Act: -0.0001

Data Index: 8983 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.2956. Min Act: -0.0001

Data Index: 570697 (C4 (Web Text))

Max Activating Token Index: 297