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

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

Neuron 1078 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: 0.3276. Min Range: -0.3276

Max Act: 0.3031. Min Act: -0.0000

Data Index: 718301 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3276. Min Act: -0.0001

Data Index: 459235 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2889. Min Act: -0.0001

Data Index: 316832 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1220482 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2956. Min Act: -0.0001

Data Index: 184432 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3054. Min Act: -0.0001

Data Index: 805741 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2793. Min Act: -0.0001

Data Index: 436002 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2681. Min Act: -0.0001

Data Index: 939137 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2676. Min Act: -0.0000

Data Index: 66525 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1314302 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2641. Min Act: -0.0001

Data Index: 10020 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2624. Min Act: -0.0001

Data Index: 712828 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2554. Min Act: -0.0000

Data Index: 402763 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2554. Min Act: -0.0000

Data Index: 428580 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2598. Min Act: -0.0001

Data Index: 22786 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2628. Min Act: -0.0001

Data Index: 399654 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2485. Min Act: -0.0000

Data Index: 956342 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2541. Min Act: -0.0001

Data Index: 574610 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.1960. Min Act: -0.0001

Data Index: 825564 (C4 (Web Text))

Max Activating Token Index: 641