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

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

Neuron 1976 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.7350. Min Act: -0.0001

Data Index: 1275314 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.7238. Min Act: -0.0001

Data Index: 1199562 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.6190. Min Act: -0.0001

Data Index: 1594120 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.6192. Min Act: -0.0001

Data Index: 1022200 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.5322. Min Act: -0.0001

Data Index: 909085 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.4948. Min Act: -0.0001

Data Index: 407463 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.3635. Min Act: -0.0001

Data Index: 1433427 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2816. Min Act: -0.0001

Data Index: 979592 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.3511. Min Act: -0.0001

Data Index: 813868 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2849. Min Act: -0.0001

Data Index: 538605 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2118. Min Act: -0.0001

Data Index: 1198053 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2591. Min Act: -0.0001

Data Index: 703242 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2804. Min Act: -0.0001

Data Index: 479377 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2322. Min Act: -0.0001

Data Index: 496589 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2709. Min Act: -0.0001

Data Index: 161907 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2993. Min Act: -0.0001

Data Index: 578210 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2525. Min Act: -0.0001

Data Index: 844008 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2482. Min Act: -0.0001

Data Index: 1062 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1044373 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.7350. Min Range: -1.7350

Max Act: 1.2325. Min Act: -0.0001

Data Index: 233603 (C4 (Web Text))

Max Activating Token Index: 187