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

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

Neuron 1075 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.9129. Min Act: -0.0001

Data Index: 427926 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8480. Min Act: -0.0001

Data Index: 475739 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.4376. Min Act: -0.0001

Data Index: 962832 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.4484. Min Act: -0.0000

Data Index: 116864 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.4855. Min Act: -0.0001

Data Index: 73257 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.4201. Min Act: -0.0000

Data Index: 104743 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.3799. Min Act: -0.0001

Data Index: 100996 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1213220 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1218260 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.3997. Min Act: -0.0001

Data Index: 125137 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1921. Min Act: -0.0001

Data Index: 885127 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1247739 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.2482. Min Act: -0.0000

Data Index: 767385 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.2104. Min Act: -0.0001

Data Index: 353633 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.2465. Min Act: -0.0001

Data Index: 1201004 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1319729 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1224153 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1810. Min Act: -0.0001

Data Index: 205332 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1324308 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.1486. Min Act: -0.0001

Data Index: 360629 (C4 (Web Text))

Max Activating Token Index: 880