Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 485 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6350. Min Act: -0.0001

Data Index: 245170 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6499. Min Act: -0.0001

Data Index: 874086 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5957. Min Act: -0.0001

Data Index: 549282 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6148. Min Act: -0.0001

Data Index: 694923 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1307101 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5984. Min Act: -0.0001

Data Index: 156529 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5770. Min Act: -0.0001

Data Index: 12918 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6190. Min Act: -0.0001

Data Index: 738166 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1324405 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5659. Min Act: -0.0001

Data Index: 331384 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5914. Min Act: -0.0001

Data Index: 263420 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1227651 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5877. Min Act: -0.0001

Data Index: 607462 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5476. Min Act: -0.0001

Data Index: 339203 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5622. Min Act: -0.0001

Data Index: 379270 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5425. Min Act: -0.0001

Data Index: 615514 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5604. Min Act: -0.0001

Data Index: 807299 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5372. Min Act: -0.0001

Data Index: 6323 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5551. Min Act: -0.0001

Data Index: 1918 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1041225 (C4 (Web Text))

Max Activating Token Index: 470