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

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

Neuron 1617 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1315507 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0003

Data Index: 556575 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0003

Data Index: 172383 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0003

Data Index: 545111 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0003

Data Index: 673478 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0003

Data Index: 544562 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0003

Data Index: 840155 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 955596 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1242833 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 196085 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 390093 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 385976 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1242974 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 495530 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 557880 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1201217 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 859824 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 35623 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 636080 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 825924 (C4 (Web Text))

Max Activating Token Index: 949