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

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

Neuron 1293 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.5410. Min Act: -0.0001

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.5240. Min Act: -0.0001

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4395. Min Act: -0.0001

Data Index: 686743 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4375. Min Act: -0.0001

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4218. Min Act: -0.0001

Data Index: 530706 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4225. Min Act: -0.0001

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3334. Min Act: -0.0001

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3881. Min Act: -0.0002

Data Index: 881334 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4235. Min Act: -0.0001

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3753. Min Act: -0.0001

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3078. Min Act: -0.0001

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3387. Min Act: -0.0001

Data Index: 1242695 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4796. Min Act: -0.0001

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3223. Min Act: -0.0001

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3607. Min Act: -0.0001

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3750. Min Act: -0.0001

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3508. Min Act: -0.0001

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3799. Min Act: -0.0001

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.3728. Min Act: -0.0001

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.2946. Min Act: -0.0001

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 111