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

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

Neuron 107 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: 0.2629. Min Range: -0.2629

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1084960 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2337. Min Act: -0.0000

Data Index: 546153 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1105710 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2267. Min Act: -0.0001

Data Index: 548344 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2192. Min Act: -0.0001

Data Index: 241282 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2268. Min Act: -0.0001

Data Index: 288539 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2159. Min Act: -0.0001

Data Index: 234036 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1272816 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2050. Min Act: -0.0000

Data Index: 38465 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2069. Min Act: -0.0000

Data Index: 885238 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2098. Min Act: -0.0001

Data Index: 778141 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1983. Min Act: -0.0000

Data Index: 739512 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2106. Min Act: -0.0001

Data Index: 310663 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1953. Min Act: -0.0001

Data Index: 993224 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1947. Min Act: -0.0000

Data Index: 801778 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1177720 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1069285 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1348271 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1980. Min Act: -0.0001

Data Index: 613246 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1907. Min Act: -0.0000

Data Index: 448624 (C4 (Web Text))

Max Activating Token Index: 468