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

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

Neuron 2803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0994. Min Range: -3.0994

Max Act: 3.0994. Min Act: -0.0000

Data Index: 402408 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.6068. Min Act: -0.0000

Data Index: 287507 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.6053. Min Act: -0.0000

Data Index: 181645 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.6540. Min Act: -0.0000

Data Index: 431245 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.6546. Min Act: -0.0000

Data Index: 21076 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.4942. Min Act: -0.0000

Data Index: 222005 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5834. Min Act: -0.0000

Data Index: 1267387 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5814. Min Act: -0.0000

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5659. Min Act: -0.0000

Data Index: 920659 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.4337. Min Act: -0.0000

Data Index: 850639 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5253. Min Act: -0.0000

Data Index: 1293253 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.3758. Min Act: -0.0000

Data Index: 921257 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5097. Min Act: -0.0000

Data Index: 286732 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.4923. Min Act: -0.0000

Data Index: 509843 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.3587. Min Act: -0.0000

Data Index: 246213 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.3411. Min Act: -0.0000

Data Index: 673126 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.3453. Min Act: -0.0000

Data Index: 1199259 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.4655. Min Act: -0.0000

Data Index: 904576 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.5575. Min Act: -0.0000

Data Index: 899817 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 3.0994. Min Range: -3.0994

Max Act: 2.4446. Min Act: -0.0000

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 596