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

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

Neuron 1786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0000

Data Index: 514341 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7152. Min Act: -0.0000

Data Index: 387007 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6766. Min Act: -0.0000

Data Index: 198093 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6509. Min Act: -0.0000

Data Index: 123552 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6070. Min Act: -0.0000

Data Index: 306249 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5701. Min Act: -0.0000

Data Index: 269883 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5912. Min Act: -0.0000

Data Index: 457561 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5627. Min Act: -0.0000

Data Index: 403924 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1206384 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5548. Min Act: -0.0000

Data Index: 267396 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1216859 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5545. Min Act: -0.0000

Data Index: 646777 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1070904 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1082253 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1287074 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1226851 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1015570 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4871. Min Act: -0.0000

Data Index: 860719 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1102599 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4824. Min Act: -0.0000

Data Index: 202142 (C4 (Web Text))

Max Activating Token Index: 16