Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1416 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.0894. Min Range: -6.0894
Max Act: 6.0581. Min Act: -0.1700
Data Index: 849568 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9644. Min Act: -0.1700
Data Index: 602724 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9956. Min Act: -0.1700
Data Index: 1161177 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0894. Min Range: -6.0894
Max Act: 6.0269. Min Act: -0.1700
Data Index: 656759 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9956. Min Act: -0.1700
Data Index: 974831 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0894. Min Range: -6.0894
Max Act: 6.0269. Min Act: -0.1700
Data Index: 95220 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.8706. Min Act: -0.1700
Data Index: 100449 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0894. Min Range: -6.0894
Max Act: 6.0894. Min Act: -0.1700
Data Index: 996962 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9331. Min Act: -0.1700
Data Index: 900816 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.7769. Min Act: -0.1700
Data Index: 887535 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9956. Min Act: -0.1700
Data Index: 441157 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.8394. Min Act: -0.1700
Data Index: 42540 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.8706. Min Act: -0.1700
Data Index: 391358 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.6206. Min Act: -0.1700
Data Index: 390730 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.8081. Min Act: -0.1700
Data Index: 436719 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9331. Min Act: -0.1700
Data Index: 721659 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.8706. Min Act: -0.1700
Data Index: 1201423 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9019. Min Act: -0.1700
Data Index: 242597 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.7769. Min Act: -0.1700
Data Index: 1158432 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0894. Min Range: -6.0894
Max Act: 5.9331. Min Act: -0.1700
Data Index: 313205 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19