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

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

Neuron 4951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.7764. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.2222. Min Act: -0.0001

Data Index: 738587 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.0597. Min Act: -0.0001

Data Index: 1199335 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.1371. Min Act: -0.0001

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.5424. Min Act: -0.0001

Data Index: 837840 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.6119. Min Act: -0.0001

Data Index: 1169179 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.6734. Min Act: -0.0001

Data Index: 1224536 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.8253. Min Act: -0.0001

Data Index: 1210595 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.3435. Min Act: -0.0001

Data Index: 858324 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.4856. Min Act: -0.0001

Data Index: 476172 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.1744. Min Act: -0.0001

Data Index: 418978 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.2733. Min Act: -0.0001

Data Index: 245566 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.5388. Min Act: -0.0001

Data Index: 682417 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.5224. Min Act: -0.0001

Data Index: 564435 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.3698. Min Act: -0.0001

Data Index: 664892 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.1727. Min Act: -0.0001

Data Index: 756838 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.1631. Min Act: -0.0001

Data Index: 964734 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 4.7764. Min Range: -4.7764

Max Act: 3.1711. Min Act: -0.0001

Data Index: 1157047 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 4.7764. Min Range: -4.7764

Max Act: 2.9949. Min Act: -0.0001

Data Index: 522858 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 4.7764. Min Range: -4.7764

Max Act: 2.9997. Min Act: -0.0001

Data Index: 1196759 (C4 (Web Text))

Max Activating Token Index: 43