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

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

Neuron 1784 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: 1.3130. Min Range: -1.3130

Max Act: 1.3130. Min Act: -0.0000

Data Index: 360300 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.2116. Min Act: -0.0000

Data Index: 192166 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1237609 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9698. Min Act: -0.0000

Data Index: 933748 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.8826. Min Act: -0.0000

Data Index: 740595 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1142965 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.7367. Min Act: -0.0000

Data Index: 943044 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6703. Min Act: -0.0001

Data Index: 761583 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1525978 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1321578 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6069. Min Act: -0.0000

Data Index: 417317 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1258667 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6308. Min Act: -0.0000

Data Index: 11794 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6065. Min Act: -0.0000

Data Index: 560830 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6318. Min Act: -0.0000

Data Index: 488852 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6363. Min Act: -0.0000

Data Index: 874745 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.6054. Min Act: -0.0000

Data Index: 142682 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.5261. Min Act: 0.0001

Data Index: 442931 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.4815. Min Act: -0.0000

Data Index: 165570 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.5851. Min Act: -0.0000

Data Index: 651656 (C4 (Web Text))

Max Activating Token Index: 1020