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

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

Neuron 5908 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4711. Min Range: -4.4711

Max Act: 4.4711. Min Act: -0.0000

Data Index: 728205 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 4.4711. Min Range: -4.4711

Max Act: 4.3213. Min Act: -0.0000

Data Index: 541660 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.9588. Min Act: -0.0000

Data Index: 839930 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.5084. Min Act: -0.0000

Data Index: 512684 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.3302. Min Act: -0.0000

Data Index: 457959 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.9322. Min Act: -0.0000

Data Index: 190272 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.9526. Min Act: -0.0000

Data Index: 431698 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.7532. Min Act: -0.0000

Data Index: 232376 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.9815. Min Act: -0.0000

Data Index: 167272 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.5884. Min Act: -0.0000

Data Index: 104673 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.6515. Min Act: -0.0000

Data Index: 727766 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.6384. Min Act: -0.0000

Data Index: 189817 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.6088. Min Act: -0.0000

Data Index: 992938 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.1664. Min Act: -0.0000

Data Index: 432962 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.4775. Min Act: -0.0000

Data Index: 316489 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.2110. Min Act: -0.0000

Data Index: 1214598 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.0377. Min Act: -0.0000

Data Index: 989562 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 4.4711. Min Range: -4.4711

Max Act: 2.0060. Min Act: -0.0000

Data Index: 796057 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 4.4711. Min Range: -4.4711

Max Act: 1.6946. Min Act: -0.0000

Data Index: 712269 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 4.4711. Min Range: -4.4711

Max Act: 1.5131. Min Act: -0.0000

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 137