Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3047 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.2009. Min Act: -0.0001
Data Index: 1568559 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1289. Min Act: -0.0001
Data Index: 1501564 (Python Code)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.9866. Min Act: -0.0001
Data Index: 158977 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.8110. Min Act: -0.0001
Data Index: 1548870 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.7148. Min Act: -0.0001
Data Index: 119072 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.7150. Min Act: -0.0000
Data Index: 1570005 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.7225. Min Act: -0.0001
Data Index: 1651588 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.7071. Min Act: -0.0001
Data Index: 1593323 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.5863. Min Act: -0.0001
Data Index: 7860 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6591. Min Act: -0.0001
Data Index: 1565063 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.7011. Min Act: -0.0001
Data Index: 774805 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6500. Min Act: -0.0000
Data Index: 220082 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6612. Min Act: -0.0000
Data Index: 1545512 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.5877. Min Act: -0.0001
Data Index: 1363316 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6282. Min Act: -0.0001
Data Index: 1478147 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6303. Min Act: -0.0001
Data Index: 1084091 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6656. Min Act: -0.0001
Data Index: 1004139 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.6044. Min Act: -0.0001
Data Index: 1489873 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.5351. Min Act: -0.0001
Data Index: 1331315 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2009. Min Range: -2.2009
Max Act: 1.4063. Min Act: -0.0001
Data Index: 1597746 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19