Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3041 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.5127. Min Act: -0.0001
Data Index: 1564552 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4452. Min Act: -0.0001
Data Index: 1629778 (Python Code)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4815. Min Act: -0.0001
Data Index: 1600531 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4650. Min Act: -0.0001
Data Index: 1528069 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.3946. Min Act: -0.0001
Data Index: 1605152 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4473. Min Act: -0.0001
Data Index: 1535556 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4197. Min Act: -0.0001
Data Index: 1383370 (Python Code)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4140. Min Act: -0.0001
Data Index: 1573126 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4326. Min Act: -0.0001
Data Index: 1533881 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4550. Min Act: -0.0001
Data Index: 1529287 (Python Code)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4273. Min Act: -0.0001
Data Index: 1595595 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4388. Min Act: -0.0001
Data Index: 1639851 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.3927. Min Act: -0.0001
Data Index: 1377842 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4060. Min Act: -0.0001
Data Index: 1613704 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4086. Min Act: -0.0001
Data Index: 1564616 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.3929. Min Act: -0.0001
Data Index: 1411215 (Python Code)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4082. Min Act: -0.0001
Data Index: 1367303 (Python Code)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4070. Min Act: -0.0001
Data Index: 1377376 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.3850. Min Act: -0.0001
Data Index: 1548050 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5127. Min Range: -0.5127
Max Act: 0.4087. Min Act: -0.0001
Data Index: 1430931 (Python Code)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19