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

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

Neuron 114 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.6764. Min Act: -0.0000

Data Index: 333627 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.4931. Min Act: -0.0000

Data Index: 217468 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.5972. Min Act: -0.0000

Data Index: 756076 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.6219. Min Act: -0.0000

Data Index: 580439 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.4970. Min Act: -0.0000

Data Index: 698767 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.4728. Min Act: -0.0000

Data Index: 624785 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3798. Min Act: -0.0000

Data Index: 123626 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1143351 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1305868 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3007. Min Act: -0.0000

Data Index: 572067 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.1705. Min Act: -0.0000

Data Index: 1318129 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3530. Min Act: -0.0000

Data Index: 412589 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3289. Min Act: -0.0000

Data Index: 923422 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3036. Min Act: -0.0000

Data Index: 180231 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3593. Min Act: -0.0000

Data Index: 315358 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.3125. Min Act: -0.0000

Data Index: 276379 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.2840. Min Act: -0.0000

Data Index: 588982 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.1961. Min Act: -0.0000

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.1953. Min Act: -0.0000

Data Index: 80785 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.6764. Min Range: -1.6764

Max Act: 1.0745. Min Act: -0.0000

Data Index: 857659 (C4 (Web Text))

Max Activating Token Index: 474