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

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

Neuron 851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6854. Min Range: -5.6854

Max Act: 5.6854. Min Act: -0.0001

Data Index: 187608 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.7001. Min Act: -0.0000

Data Index: 670172 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.4900. Min Act: -0.0000

Data Index: 391320 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.5151. Min Act: -0.0001

Data Index: 1157348 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.4101. Min Act: -0.0001

Data Index: 101704 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.5330. Min Act: -0.0001

Data Index: 1107188 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.3629. Min Act: -0.0000

Data Index: 701657 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.2141. Min Act: -0.0001

Data Index: 1347344 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.1921. Min Act: -0.0001

Data Index: 455619 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.1558. Min Act: -0.0001

Data Index: 501639 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 5.6854. Min Range: -5.6854

Max Act: 3.8468. Min Act: -0.0001

Data Index: 472152 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.3099. Min Act: -0.0001

Data Index: 73372 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.0982. Min Act: -0.0001

Data Index: 830658 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.0891. Min Act: -0.0000

Data Index: 470282 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.0744. Min Act: -0.0001

Data Index: 564179 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 5.6854. Min Range: -5.6854

Max Act: 4.1943. Min Act: -0.0001

Data Index: 711223 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.6854. Min Range: -5.6854

Max Act: 3.8442. Min Act: -0.0001

Data Index: 1325264 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 5.6854. Min Range: -5.6854

Max Act: 3.8439. Min Act: -0.0000

Data Index: 762756 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 5.6854. Min Range: -5.6854

Max Act: 3.8217. Min Act: -0.0000

Data Index: 675694 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 5.6854. Min Range: -5.6854

Max Act: 3.8017. Min Act: -0.0001

Data Index: 904266 (C4 (Web Text))

Max Activating Token Index: 436