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

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

Neuron 3468 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8847. Min Act: -0.0002

Data Index: 883586 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8601. Min Act: -0.0002

Data Index: 85529 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8673. Min Act: -0.0002

Data Index: 951486 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8935. Min Act: -0.0002

Data Index: 1269374 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8826. Min Act: -0.0002

Data Index: 776199 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8593. Min Act: -0.0002

Data Index: 318923 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8689. Min Act: -0.0002

Data Index: 132878 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8406. Min Act: -0.0002

Data Index: 1205615 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8238. Min Act: -0.0002

Data Index: 135 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8194. Min Act: -0.0002

Data Index: 445483 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8387. Min Act: -0.0002

Data Index: 1478350 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8086. Min Act: -0.0002

Data Index: 159238 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8042. Min Act: -0.0002

Data Index: 248659 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7977. Min Act: -0.0002

Data Index: 419673 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7673. Min Act: -0.0002

Data Index: 438249 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7751. Min Act: -0.0002

Data Index: 1124558 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7534. Min Act: -0.0002

Data Index: 442667 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7547. Min Act: -0.0002

Data Index: 1272026 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7527. Min Act: -0.0002

Data Index: 999104 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7467. Min Act: -0.0002

Data Index: 398819 (C4 (Web Text))

Max Activating Token Index: 501