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

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

Neuron 1369 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: 5.0981. Min Range: -5.0981

Max Act: 5.0059. Min Act: -0.0001

Data Index: 189141 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 5.0981. Min Range: -5.0981

Max Act: 5.0981. Min Act: -0.0001

Data Index: 760218 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.3069. Min Act: -0.0000

Data Index: 982505 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.6416. Min Act: -0.0001

Data Index: 1170394 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.8064. Min Act: -0.0001

Data Index: 615021 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1900. Min Act: -0.0000

Data Index: 755422 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1299. Min Act: -0.0001

Data Index: 61863 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.3390. Min Act: -0.0001

Data Index: 1353227 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.0953. Min Act: -0.0001

Data Index: 99506 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1146. Min Act: -0.0001

Data Index: 421377 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.2939. Min Act: -0.0001

Data Index: 811487 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.2378. Min Act: -0.0001

Data Index: 153648 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 5.0981. Min Range: -5.0981

Max Act: 3.9703. Min Act: -0.0001

Data Index: 389548 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.3826. Min Act: -0.0001

Data Index: 625962 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1935. Min Act: -0.0001

Data Index: 880191 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.3042. Min Act: -0.0000

Data Index: 278821 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 5.0981. Min Range: -5.0981

Max Act: 3.9710. Min Act: -0.0001

Data Index: 1130306 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1333. Min Act: -0.0001

Data Index: 66832 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.1073. Min Act: -0.0001

Data Index: 514987 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 5.0981. Min Range: -5.0981

Max Act: 4.2178. Min Act: -0.0001

Data Index: 949584 (C4 (Web Text))

Max Activating Token Index: 143