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

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

Neuron 429 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: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0001

Data Index: 303538 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7845. Min Act: -0.0001

Data Index: 140021 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8114. Min Act: -0.0001

Data Index: 665523 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7666. Min Act: -0.0000

Data Index: 793302 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7063. Min Act: -0.0001

Data Index: 901832 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1280469 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6794. Min Act: -0.0001

Data Index: 260950 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5948. Min Act: -0.0000

Data Index: 304080 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5905. Min Act: -0.0001

Data Index: 778727 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5742. Min Act: -0.0000

Data Index: 243360 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1336199 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6775. Min Act: -0.0001

Data Index: 883464 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6032. Min Act: -0.0000

Data Index: 133864 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5749. Min Act: -0.0001

Data Index: 1214170 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5916. Min Act: -0.0001

Data Index: 1249693 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5926. Min Act: -0.0001

Data Index: 672434 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1051565 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5343. Min Act: -0.0001

Data Index: 168905 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1249914 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5284. Min Act: -0.0000

Data Index: 222054 (C4 (Web Text))

Max Activating Token Index: 341