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

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

Neuron 4914 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: 3.6046. Min Range: -3.6046

Max Act: 3.6046. Min Act: -0.0000

Data Index: 1282258 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.4170. Min Act: -0.0000

Data Index: 1242065 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.2944. Min Act: -0.0000

Data Index: 942370 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.2059. Min Act: -0.0000

Data Index: 64851 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.1083. Min Act: -0.0000

Data Index: 155559 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.8456. Min Act: -0.0000

Data Index: 615801 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.0023. Min Act: -0.0000

Data Index: 860167 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.6123. Min Act: -0.0000

Data Index: 18428 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.9724. Min Act: -0.0000

Data Index: 763589 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.6549. Min Act: -0.0000

Data Index: 646700 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.7801. Min Act: -0.0000

Data Index: 821355 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.7419. Min Act: -0.0000

Data Index: 789952 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.4707. Min Act: -0.0000

Data Index: 1198741 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.7374. Min Act: -0.0000

Data Index: 712164 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.6438. Min Act: -0.0000

Data Index: 83337 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.6848. Min Act: -0.0000

Data Index: 549671 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.3419. Min Act: -0.0000

Data Index: 829742 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.5830. Min Act: -0.0000

Data Index: 623090 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.4270. Min Act: -0.0000

Data Index: 1032042 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 3.6046. Min Range: -3.6046

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1005181 (C4 (Web Text))

Max Activating Token Index: 578