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

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

Neuron 3693 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: 0.2939. Min Range: -0.2939

Max Act: 0.2939. Min Act: -0.0000

Data Index: 928627 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2663. Min Act: -0.0000

Data Index: 703302 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2748. Min Act: -0.0000

Data Index: 903788 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1003772 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1333346 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2555. Min Act: -0.0000

Data Index: 499122 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1043251 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2540. Min Act: 0.0000

Data Index: 733637 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2547. Min Act: -0.0000

Data Index: 169117 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2417. Min Act: -0.0000

Data Index: 50625 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2433. Min Act: -0.0000

Data Index: 311434 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2329. Min Act: -0.0000

Data Index: 829261 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2269. Min Act: -0.0000

Data Index: 154897 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2214. Min Act: -0.0000

Data Index: 639987 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2180. Min Act: -0.0000

Data Index: 404751 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2240. Min Act: -0.0000

Data Index: 589402 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2249. Min Act: -0.0000

Data Index: 821003 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1126164 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2137. Min Act: -0.0001

Data Index: 394919 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1115899 (C4 (Web Text))

Max Activating Token Index: 323