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

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

Neuron 771 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 680214 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 339139 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 43127 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1163680 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 971009 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1301973 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1358785 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 215661 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 593441 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 24116 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 971127 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1135827 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1127706 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 884775 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 969260 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 455770 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 256287 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1327374 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 74254 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 859479 (C4 (Web Text))

Max Activating Token Index: 25