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

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

Neuron 5075 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.6565. Min Act: -0.0000

Data Index: 1484335 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.9058. Min Act: -0.0000

Data Index: 1581866 (Python Code)

Max Activating Token Index: 953

Text #2

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.6771. Min Act: -0.0000

Data Index: 610804 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.5646. Min Act: -0.0000

Data Index: 934682 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.4592. Min Act: -0.0000

Data Index: 310582 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.3935. Min Act: -0.0000

Data Index: 412510 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.3580. Min Act: -0.0000

Data Index: 67441 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1118630 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1165077 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.2208. Min Act: -0.0000

Data Index: 778678 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.2176. Min Act: -0.0000

Data Index: 529765 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.2132. Min Act: -0.0000

Data Index: 244209 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1180177 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1496775 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.0769. Min Act: -0.0000

Data Index: 609230 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.1672. Min Act: -0.0000

Data Index: 674504 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.1369. Min Act: -0.0000

Data Index: 154099 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1332548 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.9058. Min Range: -1.9058

Max Act: 1.0545. Min Act: -0.0000

Data Index: 498870 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.9058. Min Range: -1.9058

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1306748 (C4 (Web Text))

Max Activating Token Index: 333