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

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

Neuron 3304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.2736. Min Act: -0.0001

Data Index: 36903 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.2994. Min Act: -0.0001

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.3489. Min Act: -0.0001

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0558. Min Act: -0.0000

Data Index: 367545 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.1029. Min Act: -0.0000

Data Index: 456582 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0016. Min Act: -0.0000

Data Index: 1257859 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7572. Min Act: -0.0000

Data Index: 928466 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.9814. Min Act: -0.0001

Data Index: 65491 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.8946. Min Act: -0.0001

Data Index: 210358 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.9322. Min Act: -0.0001

Data Index: 203789 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7220. Min Act: -0.0001

Data Index: 377509 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7308. Min Act: -0.0000

Data Index: 844654 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7100. Min Act: -0.0000

Data Index: 132287 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.5803. Min Act: -0.0001

Data Index: 617401 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6099. Min Act: -0.0001

Data Index: 591694 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.2924. Min Act: -0.0001

Data Index: 1352145 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.4318. Min Act: -0.0001

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6285. Min Act: -0.0000

Data Index: 176412 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.3647. Min Act: -0.0000

Data Index: 466854 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.4113. Min Act: -0.0000

Data Index: 13492 (C4 (Web Text))

Max Activating Token Index: 242