Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1817 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9769. Min Act: -0.1700
Data Index: 1208250 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9769. Min Act: -0.1700
Data Index: 70051 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0081. Min Range: -6.0081
Max Act: 6.0081. Min Act: -0.1700
Data Index: 74118 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9456. Min Act: -0.1700
Data Index: 224108 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9769. Min Act: -0.1700
Data Index: 575619 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9144. Min Act: -0.1700
Data Index: 518398 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9144. Min Act: -0.1700
Data Index: 678611 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9144. Min Act: -0.1700
Data Index: 90185 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9456. Min Act: -0.1700
Data Index: 862031 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8519. Min Act: -0.1700
Data Index: 220568 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8519. Min Act: -0.1700
Data Index: 1108802 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8831. Min Act: -0.1700
Data Index: 656582 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8831. Min Act: -0.1700
Data Index: 302910 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.7894. Min Act: -0.1700
Data Index: 920346 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.9456. Min Act: -0.1700
Data Index: 1267276 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8206. Min Act: -0.1700
Data Index: 32079 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.7894. Min Act: -0.1700
Data Index: 522820 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8206. Min Act: -0.1700
Data Index: 712230 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8519. Min Act: -0.1700
Data Index: 851027 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0081. Min Range: -6.0081
Max Act: 5.8831. Min Act: -0.1700
Data Index: 607520 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19