Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 901 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.8047. Min Act: -0.1700
Data Index: 268711 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.8206. Min Act: -0.1700
Data Index: 1333154 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7728. Min Act: -0.1700
Data Index: 86054 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7569. Min Act: -0.1700
Data Index: 730271 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7249. Min Act: -0.1700
Data Index: 575718 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7249. Min Act: -0.1700
Data Index: 133661 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7409. Min Act: -0.1700
Data Index: 1045408 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.7090. Min Act: -0.1700
Data Index: 20855 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6929. Min Act: -0.1700
Data Index: 376555 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6929. Min Act: -0.1700
Data Index: 1248911 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6769. Min Act: -0.1700
Data Index: 1257421 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6929. Min Act: -0.1700
Data Index: 115856 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6609. Min Act: -0.1700
Data Index: 22841 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6609. Min Act: -0.1700
Data Index: 1216196 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6769. Min Act: -0.1700
Data Index: 373223 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6769. Min Act: -0.1700
Data Index: 12073 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6609. Min Act: -0.1700
Data Index: 601557 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6769. Min Act: -0.1700
Data Index: 790873 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6609. Min Act: -0.1700
Data Index: 361383 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8206. Min Range: -2.8206
Max Act: 2.6769. Min Act: -0.1700
Data Index: 899326 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19