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

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

Neuron 2021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3053. Min Act: -0.0000

Data Index: 486709 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2662. Min Act: -0.0000

Data Index: 671068 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1027765 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2445. Min Act: -0.0000

Data Index: 864057 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2194. Min Act: -0.0000

Data Index: 218565 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1154009 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2196. Min Act: -0.0000

Data Index: 294202 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2093. Min Act: -0.0000

Data Index: 902284 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2193. Min Act: -0.0000

Data Index: 576773 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1044294 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2004. Min Act: -0.0000

Data Index: 635537 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2091. Min Act: -0.0000

Data Index: 607347 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2276. Min Act: -0.0000

Data Index: 771617 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1019684 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1987. Min Act: -0.0000

Data Index: 220977 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1986. Min Act: -0.0000

Data Index: 203183 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1264214 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2149. Min Act: -0.0000

Data Index: 737019 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1201489 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1974. Min Act: -0.0000

Data Index: 633468 (C4 (Web Text))

Max Activating Token Index: 826