Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2750 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3753. Min Act: -0.0000

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3611. Min Act: -0.0000

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1104579 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3794. Min Act: -0.0001

Data Index: 683225 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3889. Min Act: -0.0000

Data Index: 820915 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3495. Min Act: -0.0000

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3612. Min Act: -0.0000

Data Index: 26684 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3487. Min Act: -0.0000

Data Index: 257753 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3626. Min Act: -0.0000

Data Index: 117609 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3492. Min Act: -0.0000

Data Index: 631533 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3475. Min Act: -0.0001

Data Index: 943943 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3327. Min Act: -0.0000

Data Index: 594453 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3555. Min Act: -0.0000

Data Index: 404333 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3081. Min Act: -0.0001

Data Index: 869985 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3449. Min Act: -0.0000

Data Index: 866321 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3609. Min Act: -0.0000

Data Index: 575742 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3355. Min Act: -0.0000

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3457. Min Act: -0.0000

Data Index: 312680 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1228981 (C4 (Web Text))

Max Activating Token Index: 162