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

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

Neuron 2674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0506. Min Range: -2.0506

Max Act: 2.0506. Min Act: -0.0000

Data Index: 38213 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.7515. Min Act: -0.0000

Data Index: 471721 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.6666. Min Act: -0.0000

Data Index: 808670 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5814. Min Act: -0.0000

Data Index: 419553 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5867. Min Act: -0.0000

Data Index: 392982 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5773. Min Act: -0.0000

Data Index: 6498 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1054948 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1221321 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5021. Min Act: -0.0000

Data Index: 820987 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5320. Min Act: -0.0000

Data Index: 72431 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1152574 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4271. Min Act: -0.0000

Data Index: 746907 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.3549. Min Act: -0.0000

Data Index: 513344 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4212. Min Act: -0.0000

Data Index: 194278 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4212. Min Act: -0.0000

Data Index: 802527 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4149. Min Act: -0.0000

Data Index: 720929 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4070. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.4039. Min Act: -0.0000

Data Index: 718956 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 2.0506. Min Range: -2.0506

Max Act: 1.3162. Min Act: -0.0000

Data Index: 49394 (C4 (Web Text))

Max Activating Token Index: 663