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

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

Neuron 4669 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.3144. Min Act: -0.0000

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8928. Min Act: -0.0000

Data Index: 539297 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8249. Min Act: -0.0000

Data Index: 1539125 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.7361. Min Act: -0.0000

Data Index: 20095 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8524. Min Act: -0.0000

Data Index: 1583401 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1459099 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.3732. Min Act: -0.0000

Data Index: 1648615 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.5958. Min Act: -0.0000

Data Index: 914598 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1522273 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.4757. Min Act: -0.0000

Data Index: 1601083 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.3664. Min Act: -0.0000

Data Index: 1539763 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 3.3144. Min Range: -3.3144

Max Act: 1.6466. Min Act: -0.0000

Data Index: 197394 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 3.3144. Min Range: -3.3144

Max Act: 1.9489. Min Act: -0.0000

Data Index: 599450 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.2963. Min Act: -0.0000

Data Index: 166566 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.2416. Min Act: -0.0000

Data Index: 728990 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.1214. Min Act: -0.0000

Data Index: 1496516 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.1147. Min Act: -0.0000

Data Index: 647288 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.1933. Min Act: -0.0000

Data Index: 633222 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.0459. Min Act: -0.0000

Data Index: 52693 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.0362. Min Act: -0.0000

Data Index: 905118 (C4 (Web Text))

Max Activating Token Index: 428