Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 92 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1757. Min Act: -0.1699
Data Index: 651438 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1757. Min Act: -0.1700
Data Index: 142646 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1591. Min Act: -0.1700
Data Index: 1046266 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1425. Min Act: -0.1700
Data Index: 1231645 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1258. Min Act: -0.1699
Data Index: 44538 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1091. Min Act: -0.1700
Data Index: 591188 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1091. Min Act: -0.1700
Data Index: 307981 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0923. Min Act: -0.1700
Data Index: 1285564 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.1091. Min Act: -0.1700
Data Index: 899267 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 50671 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0756. Min Act: -0.1700
Data Index: 810599 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 988208 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0756. Min Act: -0.1700
Data Index: 1181974 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1699
Data Index: 717057 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 392286 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 599372 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 595972 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 804350 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 786486 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1757. Min Range: -2.1757
Max Act: 2.0588. Min Act: -0.1700
Data Index: 748705 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19