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

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

Neuron 1200 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.3547. Min Act: -0.0001

Data Index: 1292206 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.9728. Min Act: -0.0001

Data Index: 259043 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.9087. Min Act: -0.0001

Data Index: 1042697 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.8859. Min Act: -0.0001

Data Index: 507048 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7636. Min Act: -0.0001

Data Index: 1307374 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7647. Min Act: -0.0001

Data Index: 15225 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6660. Min Act: -0.0001

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6957. Min Act: -0.0001

Data Index: 617601 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7814. Min Act: -0.0001

Data Index: 51811 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1286291 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6763. Min Act: -0.0001

Data Index: 908758 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7091. Min Act: -0.0001

Data Index: 890310 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1093004 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6585. Min Act: -0.0001

Data Index: 375979 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1281565 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7179. Min Act: -0.0001

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1163315 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6709. Min Act: -0.0001

Data Index: 273409 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.7503. Min Act: -0.0001

Data Index: 121714 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.6668. Min Act: -0.0001

Data Index: 1344401 (C4 (Web Text))

Max Activating Token Index: 1017