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

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

Neuron 1945 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3728. Min Act: -0.0001

Data Index: 222854 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2181. Min Act: -0.0001

Data Index: 957331 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1437. Min Act: -0.0001

Data Index: 93353 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1297. Min Act: -0.0001

Data Index: 564194 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8383. Min Act: -0.0001

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0609. Min Act: -0.0001

Data Index: 822547 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1124. Min Act: -0.0001

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0232. Min Act: -0.0001

Data Index: 1181288 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0956. Min Act: -0.0001

Data Index: 339486 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9611. Min Act: -0.0001

Data Index: 1062696 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0613. Min Act: -0.0001

Data Index: 578756 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8199. Min Act: -0.0001

Data Index: 989951 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1198972 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0419. Min Act: -0.0001

Data Index: 1030954 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1599. Min Act: -0.0001

Data Index: 41038 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9581. Min Act: -0.0001

Data Index: 59796 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0283. Min Act: -0.0001

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9593. Min Act: -0.0001

Data Index: 407781 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8901. Min Act: -0.0001

Data Index: 562865 (C4 (Web Text))

Max Activating Token Index: 15