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

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

Neuron 158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4853. Min Act: -0.0001

Data Index: 571327 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4048. Min Act: -0.0001

Data Index: 378385 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2013. Min Act: -0.0001

Data Index: 691932 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.3188. Min Act: -0.0001

Data Index: 1091084 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2356. Min Act: -0.0001

Data Index: 689311 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1070357 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2500. Min Act: -0.0001

Data Index: 1205099 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2424. Min Act: -0.0001

Data Index: 800722 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2584. Min Act: -0.0001

Data Index: 707848 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2353. Min Act: -0.0001

Data Index: 736791 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2867. Min Act: -0.0001

Data Index: 311563 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1985. Min Act: -0.0001

Data Index: 261154 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1839. Min Act: -0.0001

Data Index: 1331570 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1325. Min Act: -0.0001

Data Index: 482943 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1518. Min Act: -0.0001

Data Index: 663407 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2051. Min Act: -0.0001

Data Index: 58133 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1269. Min Act: -0.0001

Data Index: 977613 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1131. Min Act: -0.0001

Data Index: 404729 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0935. Min Act: -0.0001

Data Index: 171669 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0545. Min Act: -0.0001

Data Index: 602297 (C4 (Web Text))

Max Activating Token Index: 395