Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3180 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.7919. Min Act: -0.0001
Data Index: 1516671 (Python Code)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.6102. Min Act: -0.0001
Data Index: 1407818 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.5266. Min Act: -0.0001
Data Index: 1379329 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.3944. Min Act: -0.0001
Data Index: 1533590 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.3987. Min Act: -0.0001
Data Index: 1448348 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.5004. Min Act: -0.0001
Data Index: 264392 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2574. Min Act: -0.0001
Data Index: 1494281 (Python Code)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.3311. Min Act: -0.0001
Data Index: 200740 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2271. Min Act: -0.0001
Data Index: 1616599 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.3268. Min Act: -0.0001
Data Index: 1497816 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2438. Min Act: -0.0001
Data Index: 1588281 (Python Code)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2112. Min Act: -0.0001
Data Index: 1473020 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.1595. Min Act: -0.0001
Data Index: 1538301 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2567. Min Act: -0.0001
Data Index: 1536272 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2646. Min Act: -0.0001
Data Index: 1529357 (Python Code)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2868. Min Act: -0.0001
Data Index: 1638118 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2011. Min Act: -0.0001
Data Index: 1438700 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.0523. Min Act: -0.0001
Data Index: 1368421 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.2750. Min Act: -0.0001
Data Index: 973346 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7919. Min Range: -1.7919
Max Act: 1.1268. Min Act: -0.0001
Data Index: 1471814 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19