Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2700 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.2001. Min Act: -0.0000

Data Index: 575569 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.8332. Min Act: -0.0000

Data Index: 639637 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1029791 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5881. Min Act: -0.0000

Data Index: 138592 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5554. Min Act: -0.0000

Data Index: 429119 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.6929. Min Act: -0.0000

Data Index: 1075649 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1541314 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.7727. Min Act: -0.0000

Data Index: 432935 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5700. Min Act: -0.0000

Data Index: 422724 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5777. Min Act: -0.0000

Data Index: 336290 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.4114. Min Act: -0.0000

Data Index: 82309 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5441. Min Act: -0.0000

Data Index: 1192320 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5213. Min Act: -0.0000

Data Index: 466844 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5097. Min Act: -0.0000

Data Index: 1322868 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5030. Min Act: -0.0000

Data Index: 1579568 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.3618. Min Act: -0.0000

Data Index: 114771 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.5807. Min Act: -0.0000

Data Index: 1143593 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1312051 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.4347. Min Act: -0.0000

Data Index: 576822 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.2865. Min Act: -0.0000

Data Index: 723423 (C4 (Web Text))

Max Activating Token Index: 446