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

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

Neuron 2615 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8764. Min Act: -0.0003

Data Index: 79109 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8794. Min Act: -0.0003

Data Index: 641133 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8996. Min Act: -0.0003

Data Index: 38070 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8428. Min Act: -0.0003

Data Index: 925010 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8927. Min Act: -0.0003

Data Index: 937183 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8272. Min Act: -0.0003

Data Index: 967531 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8908. Min Act: -0.0003

Data Index: 1133278 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7610. Min Act: -0.0003

Data Index: 1265700 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6959. Min Act: -0.0003

Data Index: 227763 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7555. Min Act: -0.0003

Data Index: 506553 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8008. Min Act: -0.0003

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7577. Min Act: -0.0003

Data Index: 724575 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7391. Min Act: -0.0003

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7943. Min Act: -0.0003

Data Index: 870025 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7611. Min Act: -0.0003

Data Index: 1146089 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7194. Min Act: -0.0003

Data Index: 481303 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7608. Min Act: -0.0003

Data Index: 282137 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8293. Min Act: -0.0003

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6872. Min Act: -0.0003

Data Index: 752727 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7552. Min Act: -0.0003

Data Index: 139193 (C4 (Web Text))

Max Activating Token Index: 74