Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 1219391 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 399381 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.5991. Min Act: -0.1700
Data Index: 1065264 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.5991. Min Act: -0.1700
Data Index: 290686 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.5991. Min Act: -0.1700
Data Index: 1356657 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.5366. Min Act: -0.1700
Data Index: 1336764 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.4741. Min Act: -0.1700
Data Index: 797422 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.4116. Min Act: -0.1700
Data Index: 441793 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.4116. Min Act: -0.1697
Data Index: 229418 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3804. Min Act: -0.1700
Data Index: 1319176 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3179. Min Act: -0.1700
Data Index: 51488 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3804. Min Act: -0.1700
Data Index: 314542 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3804. Min Act: -0.1700
Data Index: 1002007 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3491. Min Act: -0.1700
Data Index: 567749 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3804. Min Act: -0.1700
Data Index: 687546 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3491. Min Act: -0.1700
Data Index: 187377 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3491. Min Act: -0.1700
Data Index: 496014 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1170725 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3491. Min Act: -0.1700
Data Index: 1240023 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6929. Min Range: -4.6929
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1311451 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19