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

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

Neuron 5116 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9442. Min Act: -0.0000

Data Index: 679902 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 2.0565. Min Range: -2.0565

Max Act: 2.0398. Min Act: -0.0000

Data Index: 820457 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9223. Min Act: -0.0000

Data Index: 88121 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9692. Min Act: -0.0000

Data Index: 278230 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 2.0565. Min Range: -2.0565

Max Act: 2.0565. Min Act: -0.0000

Data Index: 238248 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9446. Min Act: -0.0000

Data Index: 1135414 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9230. Min Act: -0.0000

Data Index: 786815 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.8763. Min Act: -0.0000

Data Index: 456309 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.9345. Min Act: -0.0000

Data Index: 134329 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.8890. Min Act: -0.0000

Data Index: 671957 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.7835. Min Act: -0.0000

Data Index: 701011 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1159943 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.6469. Min Act: -0.0000

Data Index: 768647 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.7131. Min Act: -0.0000

Data Index: 1009064 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1018000 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.5918. Min Act: -0.0000

Data Index: 69023 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.6704. Min Act: -0.0000

Data Index: 809469 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.7325. Min Act: -0.0000

Data Index: 290086 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.6360. Min Act: -0.0000

Data Index: 1061072 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.0565. Min Range: -2.0565

Max Act: 1.6275. Min Act: -0.0000

Data Index: 64316 (C4 (Web Text))

Max Activating Token Index: 832