Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1593 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5801. Min Act: -0.1700
Data Index: 929665 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5479. Min Act: -0.1700
Data Index: 1311244 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5317. Min Act: -0.1700
Data Index: 285671 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5317. Min Act: -0.1700
Data Index: 522449 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5317. Min Act: -0.1700
Data Index: 905132 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 1203791 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 875693 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 291439 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 813609 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 1268852 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 618360 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 621131 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 358060 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 141505 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.5156. Min Act: -0.1700
Data Index: 1233877 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4832. Min Act: -0.1700
Data Index: 317609 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 869718 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 757514 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 511562 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5801. Min Range: -2.5801
Max Act: 2.4994. Min Act: -0.1700
Data Index: 49349 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19