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

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

Neuron 564 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.4208. Min Act: -0.0000

Data Index: 395275 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3838. Min Act: -0.0000

Data Index: 495334 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1341026 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1333661 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3502. Min Act: -0.0000

Data Index: 2051 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3512. Min Act: -0.0000

Data Index: 235086 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3236. Min Act: -0.0000

Data Index: 836074 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3093. Min Act: -0.0000

Data Index: 450424 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1005756 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2939. Min Act: -0.0000

Data Index: 814289 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3061. Min Act: -0.0000

Data Index: 172767 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3022. Min Act: -0.0000

Data Index: 269462 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1259344 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3109. Min Act: -0.0000

Data Index: 172278 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2972. Min Act: -0.0000

Data Index: 496172 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2944. Min Act: -0.0000

Data Index: 948811 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2848. Min Act: -0.0000

Data Index: 846474 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2848. Min Act: -0.0000

Data Index: 85018 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1295768 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1173270 (C4 (Web Text))

Max Activating Token Index: 127