Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6753. Min Act: -0.0001

Data Index: 1084059 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6885. Min Act: -0.0001

Data Index: 1060852 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3991. Min Act: -0.0001

Data Index: 1191031 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3259. Min Act: -0.0001

Data Index: 721061 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3329. Min Act: -0.0001

Data Index: 176734 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3553. Min Act: -0.0001

Data Index: 1168179 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3629. Min Act: -0.0001

Data Index: 535478 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3313. Min Act: -0.0001

Data Index: 1081943 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2824. Min Act: -0.0001

Data Index: 1299345 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3092. Min Act: -0.0001

Data Index: 974535 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3619. Min Act: -0.0001

Data Index: 30607 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2723. Min Act: -0.0001

Data Index: 355680 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1638. Min Act: -0.0001

Data Index: 711813 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3471. Min Act: -0.0001

Data Index: 364132 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2653. Min Act: -0.0001

Data Index: 1451685 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1655. Min Act: -0.0001

Data Index: 763179 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2710. Min Act: -0.0001

Data Index: 736770 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2688. Min Act: -0.0001

Data Index: 783656 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2037. Min Act: -0.0001

Data Index: 743319 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1964. Min Act: -0.0001

Data Index: 779207 (C4 (Web Text))

Max Activating Token Index: 334