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

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

Neuron 3579 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4049. Min Act: -0.0002

Data Index: 364336 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3784. Min Act: -0.0002

Data Index: 102541 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3693. Min Act: -0.0001

Data Index: 240680 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3784. Min Act: -0.0002

Data Index: 588143 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3535. Min Act: -0.0001

Data Index: 247067 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3416. Min Act: -0.0002

Data Index: 853468 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3437. Min Act: -0.0002

Data Index: 823662 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3146. Min Act: -0.0002

Data Index: 792578 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3160. Min Act: -0.0002

Data Index: 337487 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3163. Min Act: -0.0002

Data Index: 1013552 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3388. Min Act: -0.0001

Data Index: 967418 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3288. Min Act: -0.0002

Data Index: 733000 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3231. Min Act: -0.0001

Data Index: 23759 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3204. Min Act: -0.0001

Data Index: 205988 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3362. Min Act: -0.0001

Data Index: 535450 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3287. Min Act: -0.0002

Data Index: 1310223 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3262. Min Act: -0.0002

Data Index: 606832 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3041. Min Act: -0.0001

Data Index: 503984 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3126. Min Act: -0.0001

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3235. Min Act: -0.0002

Data Index: 720187 (C4 (Web Text))

Max Activating Token Index: 10