Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4705. Min Range: -2.4705

Max Act: 2.4705. Min Act: -0.0000

Data Index: 581866 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 2.4705. Min Range: -2.4705

Max Act: 2.1416. Min Act: -0.0000

Data Index: 709903 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.9288. Min Act: -0.0000

Data Index: 1035225 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.9534. Min Act: -0.0000

Data Index: 156215 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.7676. Min Act: -0.0000

Data Index: 708175 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.8416. Min Act: -0.0000

Data Index: 662790 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.7561. Min Act: -0.0000

Data Index: 660552 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.6954. Min Act: -0.0000

Data Index: 573255 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.6075. Min Act: -0.0000

Data Index: 92254 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.5589. Min Act: -0.0000

Data Index: 127171 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.4278. Min Act: -0.0000

Data Index: 399512 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.5806. Min Act: -0.0000

Data Index: 388472 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.7277. Min Act: -0.0000

Data Index: 417888 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.5157. Min Act: -0.0000

Data Index: 59617 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.4892. Min Act: -0.0000

Data Index: 873931 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.5130. Min Act: -0.0000

Data Index: 727397 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1162499 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.4897. Min Act: -0.0000

Data Index: 468012 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.3754. Min Act: -0.0000

Data Index: 937534 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 2.4705. Min Range: -2.4705

Max Act: 1.3999. Min Act: -0.0000

Data Index: 943489 (C4 (Web Text))

Max Activating Token Index: 966