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

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

Neuron 4401 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3973. Min Act: -0.0000

Data Index: 175034 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1129097 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3440. Min Act: -0.0000

Data Index: 51978 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3416. Min Act: -0.0000

Data Index: 61055 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3088. Min Act: -0.0000

Data Index: 692477 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3099. Min Act: -0.0000

Data Index: 919988 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3166. Min Act: -0.0000

Data Index: 360276 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1121658 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3134. Min Act: -0.0000

Data Index: 274225 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3287. Min Act: -0.0000

Data Index: 884187 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3094. Min Act: -0.0000

Data Index: 202789 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1172159 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3148. Min Act: -0.0000

Data Index: 338646 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3041. Min Act: -0.0000

Data Index: 302957 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1111360 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.2981. Min Act: -0.0000

Data Index: 520735 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.2868. Min Act: -0.0000

Data Index: 227086 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.2933. Min Act: -0.0000

Data Index: 826044 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1227339 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.3973. Min Range: -0.3973

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1142205 (C4 (Web Text))

Max Activating Token Index: 786