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

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

Neuron 1355 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3276. Min Range: -2.3276

Max Act: 2.3276. Min Act: -0.0000

Data Index: 71211 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 2.3276. Min Range: -2.3276

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 2.3276. Min Range: -2.3276

Max Act: 2.1114. Min Act: -0.0000

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.8671. Min Act: -0.0000

Data Index: 674370 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.8965. Min Act: -0.0000

Data Index: 581843 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.7904. Min Act: -0.0000

Data Index: 149160 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.6979. Min Act: -0.0000

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.6934. Min Act: -0.0000

Data Index: 253758 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.8269. Min Act: -0.0000

Data Index: 572019 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.6859. Min Act: -0.0000

Data Index: 34412 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1246189 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1309627 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.7040. Min Act: -0.0000

Data Index: 1002925 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.5702. Min Act: -0.0000

Data Index: 919059 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.6704. Min Act: -0.0000

Data Index: 344600 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1081268 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.4161. Min Act: -0.0000

Data Index: 86220 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.4498. Min Act: -0.0000

Data Index: 127085 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 2.3276. Min Range: -2.3276

Max Act: 1.5867. Min Act: -0.0000

Data Index: 624064 (C4 (Web Text))

Max Activating Token Index: 168