Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3631 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4306. Min Range: -2.4306
Max Act: 2.4306. Min Act: -0.0001
Data Index: 1458788 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4306. Min Range: -2.4306
Max Act: 2.3061. Min Act: -0.0001
Data Index: 1559609 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4306. Min Range: -2.4306
Max Act: 2.1456. Min Act: -0.0001
Data Index: 1375785 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4306. Min Range: -2.4306
Max Act: 2.0867. Min Act: -0.0001
Data Index: 1509156 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.9794. Min Act: -0.0001
Data Index: 1497407 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.9881. Min Act: -0.0001
Data Index: 1559404 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.9287. Min Act: -0.0001
Data Index: 1388568 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.9121. Min Act: -0.0001
Data Index: 1448592 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7118. Min Act: -0.0001
Data Index: 1572966 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.8623. Min Act: -0.0001
Data Index: 1383666 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7526. Min Act: -0.0001
Data Index: 1568023 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7960. Min Act: -0.0001
Data Index: 1573915 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7388. Min Act: -0.0001
Data Index: 1502348 (Python Code)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7837. Min Act: -0.0001
Data Index: 1431768 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7200. Min Act: -0.0001
Data Index: 1509044 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.8800. Min Act: -0.0001
Data Index: 1427695 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7151. Min Act: -0.0001
Data Index: 1360840 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.7652. Min Act: -0.0001
Data Index: 1584183 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.6987. Min Act: -0.0001
Data Index: 1561306 (Python Code)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4306. Min Range: -2.4306
Max Act: 1.6557. Min Act: -0.0001
Data Index: 1603924 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19