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

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

Neuron 6081 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: 0.7907. Min Range: -0.7907

Max Act: 0.7907. Min Act: -0.0000

Data Index: 215035 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5507. Min Act: 0.0000

Data Index: 857284 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5673. Min Act: 0.0000

Data Index: 194574 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5341. Min Act: 0.0000

Data Index: 89810 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5275. Min Act: 0.0000

Data Index: 408380 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4975. Min Act: 0.0000

Data Index: 506264 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5101. Min Act: -0.0000

Data Index: 973100 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5108. Min Act: 0.0001

Data Index: 275472 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1182544 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.5069. Min Act: -0.0000

Data Index: 980765 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4982. Min Act: -0.0000

Data Index: 825978 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4860. Min Act: 0.0000

Data Index: 753863 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4900. Min Act: 0.0000

Data Index: 208076 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4691. Min Act: -0.0000

Data Index: 714097 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4655. Min Act: -0.0000

Data Index: 944912 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4623. Min Act: -0.0000

Data Index: 210164 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4376. Min Act: -0.0000

Data Index: 334481 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4514. Min Act: 0.0001

Data Index: 803778 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4415. Min Act: -0.0000

Data Index: 753174 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.4384. Min Act: 0.0000

Data Index: 292905 (C4 (Web Text))

Max Activating Token Index: 459