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

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

Neuron 2531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.3356. Min Act: -0.0001

Data Index: 1394904 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0967. Min Act: -0.0001

Data Index: 683502 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0537. Min Act: -0.0001

Data Index: 1359778 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9345. Min Act: -0.0001

Data Index: 33234 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0467. Min Act: -0.0001

Data Index: 162399 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0356. Min Act: -0.0001

Data Index: 1534376 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0092. Min Act: -0.0001

Data Index: 1072592 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9541. Min Act: -0.0001

Data Index: 1543968 (Python Code)

Max Activating Token Index: 423

Text #8

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0248. Min Act: -0.0001

Data Index: 474272 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9727. Min Act: -0.0001

Data Index: 1322073 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9464. Min Act: -0.0001

Data Index: 493359 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9160. Min Act: -0.0001

Data Index: 1312428 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9782. Min Act: -0.0001

Data Index: 78526 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9288. Min Act: -0.0001

Data Index: 242992 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9156. Min Act: -0.0001

Data Index: 1038431 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9438. Min Act: -0.0001

Data Index: 712863 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.9311. Min Act: -0.0001

Data Index: 1180437 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.8822. Min Act: -0.0001

Data Index: 75600 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.3356. Min Range: -1.3356

Max Act: 0.8529. Min Act: -0.0001

Data Index: 1173353 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.3356. Min Range: -1.3356

Max Act: 1.0148. Min Act: -0.0001

Data Index: 52403 (C4 (Web Text))

Max Activating Token Index: 79