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

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

Neuron 1030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.6733. Min Act: -0.0000

Data Index: 759521 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.7671. Min Act: -0.0000

Data Index: 260118 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4519. Min Act: -0.0000

Data Index: 998048 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4481. Min Act: -0.0000

Data Index: 1196455 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.2303. Min Act: -0.0000

Data Index: 394108 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.2906. Min Act: -0.0000

Data Index: 1189859 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.1444. Min Act: -0.0000

Data Index: 1259867 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.2541. Min Act: -0.0000

Data Index: 938130 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.8965. Min Act: -0.0000

Data Index: 352807 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.0508. Min Act: -0.0000

Data Index: 874941 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.8976. Min Act: -0.0000

Data Index: 713439 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.5653. Min Act: -0.0000

Data Index: 58749 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.6512. Min Act: -0.0000

Data Index: 101190 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1096921 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.4333. Min Act: -0.0000

Data Index: 672658 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.5487. Min Act: -0.0000

Data Index: 308770 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.5439. Min Act: -0.0000

Data Index: 837149 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.6010. Min Act: -0.0000

Data Index: 1178291 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.6065. Min Act: -0.0000

Data Index: 786448 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 3.7671. Min Range: -3.7671

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1030811 (C4 (Web Text))

Max Activating Token Index: 247