Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.9276. Min Act: -0.0001

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.9082. Min Act: -0.0001

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1330817 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.8792. Min Act: -0.0001

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.7992. Min Act: -0.0001

Data Index: 533651 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.7011. Min Act: -0.0001

Data Index: 136350 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1117541 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5884. Min Act: -0.0001

Data Index: 974912 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5741. Min Act: -0.0001

Data Index: 993058 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5729. Min Act: -0.0001

Data Index: 499162 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1241993 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5545. Min Act: -0.0001

Data Index: 519045 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5450. Min Act: -0.0001

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5420. Min Act: -0.0001

Data Index: 764910 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5769. Min Act: -0.0001

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1296207 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5197. Min Act: -0.0001

Data Index: 27145 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5559. Min Act: -0.0000

Data Index: 44809 (C4 (Web Text))

Max Activating Token Index: 365