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

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

Neuron 2489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1161820 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1048227 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.4259. Min Act: -0.0001

Data Index: 72054 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.3983. Min Act: -0.0001

Data Index: 925980 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1052186 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1389436 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.3064. Min Act: -0.0001

Data Index: 20774 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2814. Min Act: -0.0001

Data Index: 781521 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1512706 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1044049 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2795. Min Act: -0.0001

Data Index: 823484 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2326. Min Act: -0.0001

Data Index: 978610 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2115. Min Act: -0.0000

Data Index: 707978 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1609754 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1647908 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2404. Min Act: -0.0001

Data Index: 94972 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1112183 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2169. Min Act: -0.0001

Data Index: 362950 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2272. Min Act: -0.0001

Data Index: 573738 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.5113. Min Range: -0.5113

Max Act: 0.2471. Min Act: -0.0000

Data Index: 558478 (C4 (Web Text))

Max Activating Token Index: 822