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

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

Neuron 2631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3980. Min Act: -0.0001

Data Index: 1021732 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1962. Min Act: -0.0001

Data Index: 286269 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2125. Min Act: -0.0001

Data Index: 1047647 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1509. Min Act: -0.0001

Data Index: 1090293 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1312. Min Act: -0.0001

Data Index: 213968 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0932. Min Act: -0.0001

Data Index: 1306278 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1130. Min Act: -0.0001

Data Index: 255621 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1071. Min Act: -0.0001

Data Index: 1194189 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1091. Min Act: -0.0001

Data Index: 1324314 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0055. Min Act: -0.0001

Data Index: 238437 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0365. Min Act: -0.0001

Data Index: 981263 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9619. Min Act: -0.0001

Data Index: 478546 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9265. Min Act: -0.0001

Data Index: 785835 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9235. Min Act: -0.0001

Data Index: 451792 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9525. Min Act: -0.0001

Data Index: 427719 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8982. Min Act: -0.0001

Data Index: 753476 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8798. Min Act: -0.0001

Data Index: 365292 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8846. Min Act: -0.0001

Data Index: 337430 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8826. Min Act: -0.0001

Data Index: 57050 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8149. Min Act: -0.0001

Data Index: 184312 (C4 (Web Text))

Max Activating Token Index: 476