Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3265. Min Range: -3.3265

Max Act: 3.3265. Min Act: -0.0000

Data Index: 686650 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.9414. Min Act: -0.0000

Data Index: 196892 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.7475. Min Act: -0.0000

Data Index: 1095039 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.7498. Min Act: -0.0000

Data Index: 823936 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.8382. Min Act: -0.0000

Data Index: 100724 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6262. Min Act: -0.0000

Data Index: 592735 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.7217. Min Act: -0.0000

Data Index: 236962 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.5847. Min Act: -0.0000

Data Index: 51160 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6846. Min Act: -0.0000

Data Index: 632913 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6798. Min Act: -0.0000

Data Index: 21173 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1018600 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6323. Min Act: -0.0000

Data Index: 831591 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6333. Min Act: -0.0000

Data Index: 18163 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.6312. Min Act: -0.0000

Data Index: 585758 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.4798. Min Act: -0.0000

Data Index: 1095461 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.4556. Min Act: -0.0000

Data Index: 208033 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.5977. Min Act: -0.0000

Data Index: 706551 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.5738. Min Act: -0.0000

Data Index: 837247 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.5525. Min Act: -0.0000

Data Index: 1055564 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 3.3265. Min Range: -3.3265

Max Act: 2.5579. Min Act: -0.0000

Data Index: 518852 (C4 (Web Text))

Max Activating Token Index: 308