Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 55 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0001

Data Index: 435969 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0616. Min Act: -0.0001

Data Index: 397428 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0001

Data Index: 347385 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0550. Min Act: -0.0001

Data Index: 178036 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0569. Min Act: -0.0001

Data Index: 329706 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1003089 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0566. Min Act: -0.0001

Data Index: 867615 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0550. Min Act: -0.0001

Data Index: 993714 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1271175 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0528. Min Act: -0.0001

Data Index: 584733 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0533. Min Act: -0.0001

Data Index: 534957 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0568. Min Act: -0.0001

Data Index: 742411 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0520. Min Act: -0.0001

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0519. Min Act: -0.0001

Data Index: 772240 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0496. Min Act: -0.0001

Data Index: 287644 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1244 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0508. Min Act: -0.0001

Data Index: 92678 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1177475 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0502. Min Act: -0.0001

Data Index: 382281 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0482. Min Act: -0.0001

Data Index: 605826 (C4 (Web Text))

Max Activating Token Index: 10