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

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

Neuron 4435 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6921. Min Act: -0.0000

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6717. Min Act: -0.0000

Data Index: 497736 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5572. Min Act: -0.0000

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5191. Min Act: -0.0000

Data Index: 431719 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4483. Min Act: -0.0000

Data Index: 293287 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4805. Min Act: -0.0000

Data Index: 454456 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1218346 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4689. Min Act: -0.0000

Data Index: 450852 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4739. Min Act: -0.0000

Data Index: 588481 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1300743 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4645. Min Act: -0.0000

Data Index: 171056 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4109. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4377. Min Act: -0.0000

Data Index: 708732 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4249. Min Act: -0.0000

Data Index: 431527 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4360. Min Act: -0.0000

Data Index: 136172 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1057083 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4144. Min Act: -0.0000

Data Index: 817710 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4398. Min Act: -0.0000

Data Index: 858959 (C4 (Web Text))

Max Activating Token Index: 250