Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4228 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5451. Min Act: -0.0000

Data Index: 843890 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1154819 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3762. Min Act: -0.0000

Data Index: 581222 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3505. Min Act: 0.0000

Data Index: 293179 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1334865 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3673. Min Act: -0.0000

Data Index: 581634 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1085702 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3038. Min Act: -0.0000

Data Index: 334919 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1194008 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2956. Min Act: -0.0000

Data Index: 156824 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3077. Min Act: -0.0000

Data Index: 801961 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1185628 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1170074 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2824. Min Act: -0.0000

Data Index: 510797 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2905. Min Act: -0.0000

Data Index: 828956 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2876. Min Act: -0.0000

Data Index: 299838 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1148135 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2930. Min Act: -0.0000

Data Index: 155631 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2910. Min Act: -0.0000

Data Index: 837261 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1271025 (C4 (Web Text))

Max Activating Token Index: 777