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

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

Neuron 2702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1942. Min Range: -2.1942

Max Act: 2.1942. Min Act: -0.0000

Data Index: 910119 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.9277. Min Act: -0.0000

Data Index: 915413 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1201597 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.4489. Min Act: -0.0000

Data Index: 620008 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2950. Min Act: -0.0000

Data Index: 460416 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1081527 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.3075. Min Act: -0.0000

Data Index: 844546 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.3620. Min Act: -0.0000

Data Index: 697627 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1049081 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.3960. Min Act: -0.0000

Data Index: 890081 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1002704 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2514. Min Act: -0.0000

Data Index: 306735 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2158. Min Act: -0.0000

Data Index: 461046 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.3937. Min Act: -0.0000

Data Index: 1131330 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2498. Min Act: -0.0000

Data Index: 166669 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.1600. Min Act: -0.0000

Data Index: 604629 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1204542 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.2089. Min Act: -0.0000

Data Index: 319878 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.1275. Min Act: -0.0000

Data Index: 559889 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.0618. Min Act: -0.0000

Data Index: 157723 (C4 (Web Text))

Max Activating Token Index: 15