Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2991 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3435. Min Range: -2.3435
Max Act: 2.3435. Min Act: -0.0001
Data Index: 852384 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6909. Min Act: -0.0001
Data Index: 498890 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6774. Min Act: -0.0001
Data Index: 1224284 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6130. Min Act: -0.0001
Data Index: 1289526 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.7684. Min Act: -0.0001
Data Index: 292414 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6722. Min Act: -0.0001
Data Index: 769362 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.5340. Min Act: -0.0001
Data Index: 755266 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.7279. Min Act: -0.0001
Data Index: 1394535 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.4644. Min Act: -0.0001
Data Index: 1437673 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6111. Min Act: -0.0001
Data Index: 308734 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.5869. Min Act: -0.0001
Data Index: 753940 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6732. Min Act: -0.0001
Data Index: 132870 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.7171. Min Act: -0.0001
Data Index: 1443470 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.4631. Min Act: -0.0001
Data Index: 1530885 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.5831. Min Act: -0.0001
Data Index: 849086 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6700. Min Act: -0.0001
Data Index: 1517868 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.4079. Min Act: -0.0000
Data Index: 1611309 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.5739. Min Act: -0.0001
Data Index: 41357 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.6116. Min Act: -0.0001
Data Index: 1450441 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3435. Min Range: -2.3435
Max Act: 1.4756. Min Act: -0.0001
Data Index: 1618680 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19