Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 90 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0004

Data Index: 278542 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2853. Min Act: -0.0004

Data Index: 778017 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2810. Min Act: -0.0004

Data Index: 456306 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2798. Min Act: -0.0004

Data Index: 868803 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2752. Min Act: -0.0004

Data Index: 777155 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2632. Min Act: -0.0004

Data Index: 834646 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2559. Min Act: -0.0004

Data Index: 1121638 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2502. Min Act: -0.0004

Data Index: 1279319 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2501. Min Act: -0.0004

Data Index: 1317563 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2475. Min Act: -0.0004

Data Index: 1042771 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2391. Min Act: -0.0004

Data Index: 625972 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2379. Min Act: -0.0004

Data Index: 1285301 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2344. Min Act: -0.0004

Data Index: 268173 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2249. Min Act: -0.0004

Data Index: 101037 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2311. Min Act: -0.0004

Data Index: 1274799 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2304. Min Act: -0.0004

Data Index: 188665 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2300. Min Act: -0.0004

Data Index: 1131068 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2295. Min Act: -0.0004

Data Index: 1309994 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2255. Min Act: -0.0004

Data Index: 103856 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2162. Min Act: -0.0005

Data Index: 434113 (C4 (Web Text))

Max Activating Token Index: 792