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

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

Neuron 2196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1451. Min Range: -1.1451

Max Act: 1.1451. Min Act: -0.0000

Data Index: 96900 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8952. Min Act: -0.0001

Data Index: 292372 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1300162 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8994. Min Act: -0.0000

Data Index: 802012 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8813. Min Act: -0.0001

Data Index: 312361 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8715. Min Act: -0.0000

Data Index: 367251 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8437. Min Act: -0.0000

Data Index: 746694 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8134. Min Act: -0.0000

Data Index: 492568 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1004013 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8246. Min Act: -0.0001

Data Index: 181054 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8188. Min Act: -0.0000

Data Index: 960018 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1272706 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8217. Min Act: -0.0001

Data Index: 81954 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8822. Min Act: -0.0001

Data Index: 174223 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7791. Min Act: -0.0001

Data Index: 1163512 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8135. Min Act: -0.0001

Data Index: 55247 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1051297 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7837. Min Act: -0.0000

Data Index: 71296 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7751. Min Act: -0.0001

Data Index: 85407 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7754. Min Act: -0.0000

Data Index: 987263 (C4 (Web Text))

Max Activating Token Index: 439