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

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

Neuron 1348 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1021135 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9589. Min Act: -0.0000

Data Index: 702473 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.6624. Min Act: -0.0000

Data Index: 620600 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.7177. Min Act: -0.0000

Data Index: 590977 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.5590. Min Act: -0.0000

Data Index: 250672 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4207. Min Act: -0.0000

Data Index: 972445 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2497. Min Act: -0.0000

Data Index: 429895 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.0771. Min Act: -0.0000

Data Index: 436715 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1155246 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1537. Min Act: -0.0000

Data Index: 216961 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2303. Min Act: -0.0000

Data Index: 823827 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.0996. Min Act: -0.0000

Data Index: 412304 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.0098. Min Act: -0.0000

Data Index: 747378 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8936. Min Act: -0.0000

Data Index: 837200 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1350503 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.0265. Min Act: -0.0000

Data Index: 675135 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1082949 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9780. Min Act: -0.0000

Data Index: 591068 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8773. Min Act: -0.0000

Data Index: 1140523 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8712. Min Act: -0.0000

Data Index: 461290 (C4 (Web Text))

Max Activating Token Index: 680