Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.3326. Min Range: -5.3326
Max Act: 5.3326. Min Act: -0.1699
Data Index: 1099833 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3326. Min Range: -5.3326
Max Act: 5.2076. Min Act: -0.1700
Data Index: 819664 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3326. Min Range: -5.3326
Max Act: 5.0826. Min Act: -0.1700
Data Index: 564758 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3326. Min Range: -5.3326
Max Act: 5.0826. Min Act: -0.1700
Data Index: 888756 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3326. Min Range: -5.3326
Max Act: 5.0826. Min Act: -0.1700
Data Index: 314948 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9889. Min Act: -0.1700
Data Index: 519420 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9889. Min Act: -0.1700
Data Index: 1085077 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9264. Min Act: -0.1698
Data Index: 1160831 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9576. Min Act: -0.1700
Data Index: 1004176 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9264. Min Act: -0.1700
Data Index: 769222 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9576. Min Act: -0.1700
Data Index: 659390 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9576. Min Act: -0.1700
Data Index: 45089 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9264. Min Act: -0.1700
Data Index: 667735 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9264. Min Act: -0.1700
Data Index: 1127609 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.8951. Min Act: -0.1700
Data Index: 624124 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.9264. Min Act: -0.1700
Data Index: 464607 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.8951. Min Act: -0.1699
Data Index: 508132 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.8951. Min Act: -0.1700
Data Index: 100379 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.8951. Min Act: -0.1700
Data Index: 526782 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3326. Min Range: -5.3326
Max Act: 4.8951. Min Act: -0.1700
Data Index: 44489 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19