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

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

Neuron 3588 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.4028. Min Act: -0.0003

Data Index: 804018 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3806. Min Act: -0.0003

Data Index: 419279 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3712. Min Act: -0.0003

Data Index: 946149 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3568. Min Act: -0.0003

Data Index: 362526 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3550. Min Act: -0.0003

Data Index: 1341901 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3534. Min Act: -0.0003

Data Index: 320254 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3533. Min Act: -0.0003

Data Index: 1203077 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3493. Min Act: -0.0003

Data Index: 509752 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3306. Min Act: -0.0003

Data Index: 846386 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3266. Min Act: -0.0003

Data Index: 861374 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3235. Min Act: -0.0003

Data Index: 95837 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2991. Min Act: -0.0003

Data Index: 687543 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3131. Min Act: -0.0003

Data Index: 765734 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3120. Min Act: -0.0003

Data Index: 204260 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3081. Min Act: -0.0003

Data Index: 1120872 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3066. Min Act: -0.0003

Data Index: 535372 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3056. Min Act: -0.0003

Data Index: 563680 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3027. Min Act: -0.0003

Data Index: 597760 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3021. Min Act: -0.0003

Data Index: 347206 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3007. Min Act: -0.0003

Data Index: 299117 (C4 (Web Text))

Max Activating Token Index: 300