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

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

Neuron 2395 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: 7.7089. Min Range: -7.7089

Max Act: 7.7089. Min Act: -0.0000

Data Index: 580908 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 7.7089. Min Range: -7.7089

Max Act: 6.8766. Min Act: -0.0000

Data Index: 1354774 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 7.7089. Min Range: -7.7089

Max Act: 6.3455. Min Act: -0.0000

Data Index: 944045 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 7.7089. Min Range: -7.7089

Max Act: 6.6091. Min Act: -0.0001

Data Index: 1143872 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 7.7089. Min Range: -7.7089

Max Act: 6.2598. Min Act: -0.0001

Data Index: 995338 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.9065. Min Act: -0.0000

Data Index: 405650 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 7.7089. Min Range: -7.7089

Max Act: 6.0985. Min Act: -0.0001

Data Index: 689955 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.6976. Min Act: -0.0001

Data Index: 1047161 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.5019. Min Act: -0.0001

Data Index: 244367 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.7974. Min Act: -0.0000

Data Index: 1322876 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.7577. Min Act: -0.0001

Data Index: 164846 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.6771. Min Act: -0.0001

Data Index: 718523 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.8052. Min Act: -0.0000

Data Index: 674164 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.7544. Min Act: -0.0001

Data Index: 1051553 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.4722. Min Act: -0.0000

Data Index: 934524 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.2767. Min Act: -0.0001

Data Index: 989125 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.0449. Min Act: -0.0001

Data Index: 1091044 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.3003. Min Act: -0.0001

Data Index: 1040520 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 7.7089. Min Range: -7.7089

Max Act: 5.2156. Min Act: -0.0001

Data Index: 790762 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 7.7089. Min Range: -7.7089

Max Act: 4.8300. Min Act: -0.0001

Data Index: 1155049 (C4 (Web Text))

Max Activating Token Index: 372