Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1683 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0831. Min Range: -5.0831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 222172 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0831. Min Range: -5.0831
Max Act: 5.0206. Min Act: -0.1700
Data Index: 222300 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1343156 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1003611 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7393. Min Act: -0.1700
Data Index: 1254302 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7706. Min Act: -0.1700
Data Index: 453892 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7081. Min Act: -0.1700
Data Index: 562521 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7081. Min Act: -0.1700
Data Index: 457543 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.7081. Min Act: -0.1700
Data Index: 619082 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6768. Min Act: -0.1700
Data Index: 565489 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6768. Min Act: -0.1700
Data Index: 891436 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6768. Min Act: -0.1700
Data Index: 769467 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6456. Min Act: -0.1700
Data Index: 937337 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6456. Min Act: -0.1700
Data Index: 373538 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6456. Min Act: -0.1700
Data Index: 1312749 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6456. Min Act: -0.1700
Data Index: 374219 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6456. Min Act: -0.1700
Data Index: 157519 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6768. Min Act: -0.1700
Data Index: 875203 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6143. Min Act: -0.1700
Data Index: 11883 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0831. Min Range: -5.0831
Max Act: 4.6143. Min Act: -0.1700
Data Index: 669292 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19