Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1057 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5445. Min Act: -0.0003

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5499. Min Act: -0.0003

Data Index: 882420 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5229. Min Act: -0.0003

Data Index: 164139 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5342. Min Act: -0.0003

Data Index: 233689 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5043. Min Act: -0.0003

Data Index: 377859 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4429. Min Act: -0.0003

Data Index: 617735 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5145. Min Act: -0.0003

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4805. Min Act: -0.0003

Data Index: 782744 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4552. Min Act: -0.0003

Data Index: 1203990 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4692. Min Act: -0.0003

Data Index: 1196703 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4677. Min Act: -0.0003

Data Index: 1093604 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4680. Min Act: -0.0003

Data Index: 262483 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4345. Min Act: -0.0003

Data Index: 250036 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4388. Min Act: -0.0003

Data Index: 281556 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4341. Min Act: -0.0003

Data Index: 498693 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4077. Min Act: -0.0003

Data Index: 116153 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.3694. Min Act: -0.0003

Data Index: 925497 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4309. Min Act: -0.0003

Data Index: 678507 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4062. Min Act: -0.0003

Data Index: 1194211 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.3943. Min Act: -0.0003

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 726