Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1823 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.2016. Min Act: -0.1700
Data Index: 1583236 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.2016. Min Act: -0.1700
Data Index: 1403470 (Python Code)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.1391. Min Act: -0.1700
Data Index: 1573696 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0766. Min Act: -0.1700
Data Index: 1451203 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.1391. Min Act: -0.1700
Data Index: 1489004 (Python Code)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0766. Min Act: -0.1700
Data Index: 1389635 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0766. Min Act: -0.1700
Data Index: 1529076 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.1078. Min Act: -0.1700
Data Index: 1637526 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0453. Min Act: -0.1700
Data Index: 1654844 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0453. Min Act: -0.1700
Data Index: 1633751 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1507504 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0140. Min Act: -0.1700
Data Index: 1647548 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1395520 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2016. Min Range: -4.2016
Max Act: 4.0140. Min Act: -0.1700
Data Index: 1405729 (Python Code)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1451390 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1483160 (Python Code)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9515. Min Act: -0.1700
Data Index: 1421975 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1374035 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1415246 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2016. Min Range: -4.2016
Max Act: 3.9515. Min Act: -0.1700
Data Index: 1618524 (Python Code)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19