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

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

Neuron 1355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 948032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0873. Min Act: -0.0001

Data Index: 579628 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0851. Min Act: -0.0001

Data Index: 542663 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0875. Min Act: -0.0001

Data Index: 768636 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0866. Min Act: -0.0001

Data Index: 235196 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0841. Min Act: -0.0001

Data Index: 143738 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0846. Min Act: -0.0002

Data Index: 36260 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0836. Min Act: -0.0001

Data Index: 159611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0831. Min Act: -0.0001

Data Index: 88169 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0836. Min Act: -0.0001

Data Index: 65179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0834. Min Act: -0.0001

Data Index: 614025 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0820. Min Act: -0.0001

Data Index: 122044 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0832. Min Act: -0.0001

Data Index: 139176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0825. Min Act: -0.0001

Data Index: 636153 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1290213 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1332061 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0838. Min Act: -0.0001

Data Index: 387446 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0818. Min Act: -0.0001

Data Index: 962993 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0815. Min Act: -0.0001

Data Index: 177293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0830. Min Act: -0.0001

Data Index: 531970 (C4 (Web Text))

Max Activating Token Index: 260