Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1748 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2607. Min Range: -3.2607
Max Act: 3.2607. Min Act: -0.1700
Data Index: 820156 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2607. Min Range: -3.2607
Max Act: 3.0402. Min Act: -0.1700
Data Index: 1645929 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1636345 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1654132 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1614310 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1595014 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1546024 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1446203 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9453. Min Act: -0.1700
Data Index: 1537836 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1402301 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1416685 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1488518 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1632485 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9295. Min Act: -0.1700
Data Index: 1506729 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9453. Min Act: -0.1700
Data Index: 1426641 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1519411 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1562411 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1406436 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9770. Min Act: -0.1700
Data Index: 1604534 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2607. Min Range: -3.2607
Max Act: 2.9295. Min Act: -0.1700
Data Index: 1374089 (Python Code)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19