Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.9020. Min Act: -0.1700
Data Index: 478702 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.9020. Min Act: -0.1700
Data Index: 1149185 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8395. Min Act: -0.1700
Data Index: 1328395 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8395. Min Act: -0.1700
Data Index: 1195479 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8082. Min Act: -0.1700
Data Index: 1059166 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8395. Min Act: -0.1700
Data Index: 229602 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8082. Min Act: -0.1700
Data Index: 706996 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7457. Min Act: -0.1700
Data Index: 1331041 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.8707. Min Act: -0.1700
Data Index: 1101821 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7770. Min Act: -0.1700
Data Index: 802956 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7145. Min Act: -0.1700
Data Index: 400698 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.6832. Min Act: -0.1700
Data Index: 680984 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7457. Min Act: -0.1700
Data Index: 476281 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7770. Min Act: -0.1700
Data Index: 715146 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7770. Min Act: -0.1700
Data Index: 498531 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7770. Min Act: -0.1700
Data Index: 717370 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.6832. Min Act: -0.1700
Data Index: 1124381 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7145. Min Act: -0.1700
Data Index: 728812 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7457. Min Act: -0.1699
Data Index: 1030224 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9020. Min Range: -4.9020
Max Act: 4.7770. Min Act: -0.1700
Data Index: 273023 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19