Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2752 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.7203. Min Act: -0.0001
Data Index: 1537407 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.8344. Min Act: -0.0001
Data Index: 1363235 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.7840. Min Act: -0.0001
Data Index: 1567761 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6849. Min Act: -0.0001
Data Index: 1616830 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.7592. Min Act: -0.0000
Data Index: 1496192 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6924. Min Act: -0.0000
Data Index: 1616129 (Python Code)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.8191. Min Act: -0.0001
Data Index: 1596952 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6983. Min Act: -0.0001
Data Index: 1434953 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6754. Min Act: -0.0000
Data Index: 1647029 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6666. Min Act: -0.0001
Data Index: 1438313 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.5251. Min Act: -0.0001
Data Index: 1447114 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6445. Min Act: -0.0001
Data Index: 1400495 (Python Code)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6473. Min Act: -0.0001
Data Index: 1551882 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.6253. Min Act: -0.0001
Data Index: 1542034 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.5856. Min Act: -0.0000
Data Index: 1454830 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.5888. Min Act: -0.0001
Data Index: 1381318 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.4640. Min Act: -0.0000
Data Index: 1448232 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.4550. Min Act: -0.0000
Data Index: 1511091 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.4521. Min Act: -0.0000
Data Index: 1606579 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8344. Min Range: -2.8344
Max Act: 2.5490. Min Act: -0.0000
Data Index: 1602155 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19