Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.4535. Min Act: -0.1700
Data Index: 152321 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.3284. Min Act: -0.1700
Data Index: 1166703 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.3284. Min Act: -0.1700
Data Index: 1531837 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.3284. Min Act: -0.1700
Data Index: 200811 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.2347. Min Act: -0.1700
Data Index: 916961 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.2659. Min Act: -0.1700
Data Index: 1131634 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1722. Min Act: -0.1700
Data Index: 1406246 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.2034. Min Act: -0.1700
Data Index: 762617 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1722. Min Act: -0.1700
Data Index: 89411 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1722. Min Act: -0.1700
Data Index: 428436 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1409. Min Act: -0.1700
Data Index: 1015270 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1409. Min Act: -0.1700
Data Index: 902491 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1722. Min Act: -0.1700
Data Index: 1014258 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1096. Min Act: -0.1700
Data Index: 359270 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1096. Min Act: -0.1700
Data Index: 1182637 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1096. Min Act: -0.1700
Data Index: 1343335 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1096. Min Act: -0.1700
Data Index: 1523387 (Python Code)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.0784. Min Act: -0.1700
Data Index: 1362388 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1409. Min Act: -0.1700
Data Index: 1521699 (Python Code)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4535. Min Range: -4.4535
Max Act: 4.1096. Min Act: -0.1700
Data Index: 778127 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19