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

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

Neuron 1911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2960. Min Act: -0.0001

Data Index: 184053 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0001

Data Index: 159547 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2715. Min Act: -0.0001

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2694. Min Act: -0.0001

Data Index: 833247 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2422. Min Act: -0.0001

Data Index: 842298 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1075146 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2401. Min Act: -0.0001

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2321. Min Act: -0.0001

Data Index: 386781 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2287. Min Act: -0.0001

Data Index: 828627 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1036444 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2143. Min Act: -0.0001

Data Index: 33905 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2052. Min Act: -0.0001

Data Index: 162900 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2098. Min Act: -0.0001

Data Index: 946184 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1376375 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2141. Min Act: -0.0001

Data Index: 265299 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2123. Min Act: -0.0001

Data Index: 1655261 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1611241 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1097238 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1475739 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1420577 (Python Code)

Max Activating Token Index: 59