Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1912 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.6778. Min Act: -0.1598
Data Index: 261076 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.6296. Min Act: -0.1700
Data Index: 884261 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.6136. Min Act: -0.1698
Data Index: 1141659 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.6136. Min Act: -0.1700
Data Index: 616899 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.6136. Min Act: -0.1700
Data Index: 187377 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5653. Min Act: -0.1027
Data Index: 1636894 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5814. Min Act: -0.1699
Data Index: 845732 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5653. Min Act: -0.1700
Data Index: 671872 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5814. Min Act: -0.1700
Data Index: 1410827 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5491. Min Act: -0.1700
Data Index: 216020 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1700
Data Index: 205510 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1700
Data Index: 1325748 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5491. Min Act: -0.1700
Data Index: 100407 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1694
Data Index: 1048467 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5491. Min Act: -0.1700
Data Index: 853438 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1700
Data Index: 1194535 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1700
Data Index: 33648 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5330. Min Act: -0.1699
Data Index: 1173100 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5168. Min Act: -0.1521
Data Index: 1081161 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6778. Min Range: -2.6778
Max Act: 2.5491. Min Act: -0.1697
Data Index: 144057 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19