Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3172 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.6645. Min Act: -0.0001
Data Index: 1573199 (Python Code)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.6037. Min Act: -0.0001
Data Index: 1437267 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.5610. Min Act: -0.0001
Data Index: 1426379 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.6804. Min Act: -0.0001
Data Index: 1465178 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.5765. Min Act: -0.0001
Data Index: 1394294 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.5423. Min Act: -0.0001
Data Index: 1542101 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.6106. Min Act: -0.0001
Data Index: 1426382 (Python Code)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4438. Min Act: -0.0001
Data Index: 1521361 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4860. Min Act: -0.0001
Data Index: 1502351 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4453. Min Act: -0.0001
Data Index: 1465556 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4574. Min Act: -0.0001
Data Index: 1456371 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3793. Min Act: -0.0001
Data Index: 1517871 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3890. Min Act: -0.0001
Data Index: 1551622 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3993. Min Act: -0.0001
Data Index: 1364595 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3723. Min Act: -0.0001
Data Index: 1501301 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3960. Min Act: -0.0001
Data Index: 1477533 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4305. Min Act: -0.0001
Data Index: 1609116 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4186. Min Act: -0.0001
Data Index: 1540713 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.3069. Min Act: -0.0001
Data Index: 1406167 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6804. Min Range: -1.6804
Max Act: 1.4633. Min Act: -0.0001
Data Index: 1401775 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19