Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1367 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0209. Min Range: -3.0209
Max Act: 3.0209. Min Act: -0.1700
Data Index: 135197 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0209. Min Range: -3.0209
Max Act: 3.0051. Min Act: -0.1700
Data Index: 551705 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0209. Min Range: -3.0209
Max Act: 3.0051. Min Act: -0.1700
Data Index: 537120 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9893. Min Act: -0.1700
Data Index: 1251395 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9893. Min Act: -0.1700
Data Index: 264527 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 299404 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 1331435 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 664953 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 174694 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 256877 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 884978 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0209. Min Range: -3.0209
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1201617 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9576. Min Act: -0.1700
Data Index: 404333 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9576. Min Act: -0.1700
Data Index: 112949 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 506841 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 737699 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9576. Min Act: -0.1700
Data Index: 517284 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 163222 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9734. Min Act: -0.1700
Data Index: 661921 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0209. Min Range: -3.0209
Max Act: 2.9893. Min Act: -0.1700
Data Index: 54737 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19