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

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

Neuron 3846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0408. Min Range: -1.0408

Max Act: 1.0408. Min Act: -0.0000

Data Index: 415588 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9869. Min Act: -0.0001

Data Index: 1193285 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.0408. Min Range: -1.0408

Max Act: 1.0004. Min Act: -0.0001

Data Index: 453541 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.0408. Min Range: -1.0408

Max Act: 1.0008. Min Act: -0.0000

Data Index: 584693 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1505291 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9032. Min Act: -0.0001

Data Index: 1091758 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1293511 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1108454 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1255292 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8913. Min Act: -0.0000

Data Index: 174968 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8299. Min Act: -0.0001

Data Index: 59024 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1410397 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1225433 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1428149 (Python Code)

Max Activating Token Index: 617

Text #14

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8100. Min Act: -0.0001

Data Index: 1545212 (Python Code)

Max Activating Token Index: 1016

Text #15

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1166190 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.7957. Min Act: -0.0001

Data Index: 633985 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8501. Min Act: -0.0001

Data Index: 589292 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8746. Min Act: -0.0001

Data Index: 897742 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8067. Min Act: -0.0001

Data Index: 960603 (C4 (Web Text))

Max Activating Token Index: 531