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

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

Neuron 3449 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1247929 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1035562 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1005533 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1288576 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1288374 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6193. Min Act: -0.0000

Data Index: 932239 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5560. Min Act: -0.0000

Data Index: 387188 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5900. Min Act: -0.0000

Data Index: 972302 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5652. Min Act: -0.0000

Data Index: 212850 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5604. Min Act: -0.0000

Data Index: 14002 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5396. Min Act: -0.0000

Data Index: 431120 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1325459 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5356. Min Act: -0.0000

Data Index: 120026 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1300689 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.4311. Min Act: -0.0000

Data Index: 382772 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5445. Min Act: -0.0000

Data Index: 57949 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.3929. Min Act: -0.0000

Data Index: 643756 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1109280 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.4344. Min Act: -0.0000

Data Index: 723438 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1210579 (C4 (Web Text))

Max Activating Token Index: 130