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

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

Neuron 3107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4980. Min Act: -0.0001

Data Index: 281466 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.5108. Min Act: -0.0001

Data Index: 845259 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1095236 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4432. Min Act: -0.0000

Data Index: 799949 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4174. Min Act: -0.0001

Data Index: 554923 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4149. Min Act: -0.0001

Data Index: 519371 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4215. Min Act: -0.0000

Data Index: 463521 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4340. Min Act: -0.0001

Data Index: 22940 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4085. Min Act: -0.0000

Data Index: 767687 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3843. Min Act: -0.0001

Data Index: 102205 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3926. Min Act: -0.0000

Data Index: 902986 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1076742 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3611. Min Act: -0.0001

Data Index: 466541 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3700. Min Act: -0.0000

Data Index: 610381 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3559. Min Act: -0.0000

Data Index: 714369 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3749. Min Act: -0.0001

Data Index: 488559 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3606. Min Act: -0.0001

Data Index: 931638 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3139. Min Act: -0.0000

Data Index: 324149 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3229. Min Act: -0.0001

Data Index: 501159 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3533. Min Act: -0.0000

Data Index: 299554 (C4 (Web Text))

Max Activating Token Index: 933