Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2281 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.6286. Min Act: -0.0001
Data Index: 1642420 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.5025. Min Act: -0.0001
Data Index: 1473599 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.5594. Min Act: -0.0001
Data Index: 1628201 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4648. Min Act: -0.0001
Data Index: 1378199 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.5027. Min Act: -0.0001
Data Index: 1432698 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4955. Min Act: -0.0001
Data Index: 1442800 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4833. Min Act: -0.0001
Data Index: 1520756 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4839. Min Act: -0.0001
Data Index: 1582007 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4469. Min Act: -0.0001
Data Index: 1603124 (Python Code)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4899. Min Act: -0.0001
Data Index: 1427435 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4402. Min Act: -0.0001
Data Index: 1446318 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4215. Min Act: -0.0001
Data Index: 1626794 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4585. Min Act: -0.0001
Data Index: 1632312 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4642. Min Act: -0.0001
Data Index: 1433296 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4560. Min Act: -0.0001
Data Index: 1628900 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4795. Min Act: -0.0001
Data Index: 1549172 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4625. Min Act: -0.0001
Data Index: 1362634 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4883. Min Act: -0.0001
Data Index: 1571556 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4734. Min Act: -0.0001
Data Index: 1536031 (Python Code)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6286. Min Range: -0.6286
Max Act: 0.4963. Min Act: -0.0001
Data Index: 1447911 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19