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

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

Neuron 2827 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.0001

Data Index: 568166 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.0907. Min Act: -0.0001

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9588. Min Act: -0.0001

Data Index: 580139 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.0501. Min Act: -0.0001

Data Index: 1034647 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7049. Min Act: -0.0001

Data Index: 785857 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7163. Min Act: -0.0001

Data Index: 82544 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6079. Min Act: -0.0001

Data Index: 1257569 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6910. Min Act: -0.0001

Data Index: 1358784 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6215. Min Act: -0.0001

Data Index: 870185 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6549. Min Act: -0.0001

Data Index: 322187 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6233. Min Act: -0.0001

Data Index: 216691 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6545. Min Act: -0.0001

Data Index: 468958 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5969. Min Act: -0.0001

Data Index: 115001 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5975. Min Act: -0.0000

Data Index: 637601 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6268. Min Act: -0.0001

Data Index: 166872 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6318. Min Act: -0.0001

Data Index: 971161 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.4589. Min Act: -0.0001

Data Index: 1198085 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5620. Min Act: -0.0001

Data Index: 250026 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5549. Min Act: -0.0001

Data Index: 841157 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5119. Min Act: -0.0001

Data Index: 1156603 (C4 (Web Text))

Max Activating Token Index: 444