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

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

Neuron 4024 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: 3.2583. Min Range: -3.2583

Max Act: 3.2583. Min Act: -0.0000

Data Index: 1324897 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.4984. Min Act: -0.0000

Data Index: 1187385 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.6921. Min Act: -0.0000

Data Index: 1036858 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.4776. Min Act: -0.0000

Data Index: 786696 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.3736. Min Act: -0.0000

Data Index: 527530 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.2937. Min Act: -0.0000

Data Index: 617921 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.1761. Min Act: -0.0000

Data Index: 322787 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 3.2583. Min Range: -3.2583

Max Act: 2.1291. Min Act: -0.0000

Data Index: 69193 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.9372. Min Act: -0.0000

Data Index: 844322 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.9307. Min Act: -0.0000

Data Index: 408463 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.8328. Min Act: -0.0000

Data Index: 948654 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.9090. Min Act: -0.0000

Data Index: 301092 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.8550. Min Act: -0.0000

Data Index: 1118184 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.9778. Min Act: -0.0000

Data Index: 455981 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1078299 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.7957. Min Act: -0.0000

Data Index: 785094 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.7731. Min Act: -0.0000

Data Index: 571369 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.7278. Min Act: -0.0000

Data Index: 780004 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.7522. Min Act: -0.0000

Data Index: 776677 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 3.2583. Min Range: -3.2583

Max Act: 1.8332. Min Act: -0.0000

Data Index: 480849 (C4 (Web Text))

Max Activating Token Index: 388