Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 608 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0085. Min Act: -0.0003

Data Index: 91727 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1104179 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0003

Data Index: 390312 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1334879 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1326556 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0003

Data Index: 62196 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0062. Min Act: -0.0003

Data Index: 498762 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0061. Min Act: -0.0003

Data Index: 698073 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1374528 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0056. Min Act: -0.0003

Data Index: 562191 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0056. Min Act: -0.0003

Data Index: 860372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1070884 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0054. Min Act: -0.0003

Data Index: 717416 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1597408 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0053. Min Act: -0.0004

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1311010 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0053. Min Act: -0.0003

Data Index: 579972 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0054. Min Act: -0.0003

Data Index: 379059 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0053. Min Act: -0.0003

Data Index: 287749 (C4 (Web Text))

Max Activating Token Index: 79