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

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

Neuron 5475 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6666. Min Range: -5.6666

Max Act: 5.5806. Min Act: -0.0000

Data Index: 757538 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 5.6666. Min Range: -5.6666

Max Act: 5.6666. Min Act: -0.0000

Data Index: 999556 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.6628. Min Act: -0.0000

Data Index: 834587 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.8421. Min Act: -0.0000

Data Index: 943636 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.6599. Min Act: -0.0000

Data Index: 198166 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.5703. Min Act: -0.0000

Data Index: 1325173 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.9966. Min Act: -0.0000

Data Index: 262510 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.4329. Min Act: -0.0000

Data Index: 1101108 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.5412. Min Act: -0.0000

Data Index: 95376 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.6666. Min Range: -5.6666

Max Act: 4.2115. Min Act: -0.0000

Data Index: 698146 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.5948. Min Act: -0.0000

Data Index: 380191 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.7452. Min Act: -0.0000

Data Index: 989591 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.9970. Min Act: -0.0000

Data Index: 754120 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.6874. Min Act: -0.0000

Data Index: 1066528 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.7426. Min Act: -0.0000

Data Index: 1233232 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.5899. Min Act: -0.0000

Data Index: 235517 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.3783. Min Act: -0.0000

Data Index: 771275 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.5213. Min Act: -0.0000

Data Index: 1353734 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.4673. Min Act: -0.0000

Data Index: 666161 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 5.6666. Min Range: -5.6666

Max Act: 3.6641. Min Act: -0.0000

Data Index: 1176139 (C4 (Web Text))

Max Activating Token Index: 690