Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1995 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.7729. Min Act: -0.1700
Data Index: 839267 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6930. Min Act: -0.1700
Data Index: 242882 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6930. Min Act: -0.1700
Data Index: 1116736 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6930. Min Act: -0.1700
Data Index: 1209326 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6770. Min Act: -0.1700
Data Index: 1189315 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6610. Min Act: -0.1700
Data Index: 359989 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6770. Min Act: -0.1700
Data Index: 309097 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6770. Min Act: -0.1700
Data Index: 1040020 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6610. Min Act: -0.1700
Data Index: 314056 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6610. Min Act: -0.1700
Data Index: 876217 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6289. Min Act: -0.1700
Data Index: 622931 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6449. Min Act: -0.1700
Data Index: 1352458 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6289. Min Act: -0.1700
Data Index: 703109 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6289. Min Act: -0.1700
Data Index: 387615 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6449. Min Act: -0.1700
Data Index: 659824 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6289. Min Act: -0.1700
Data Index: 1101676 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6128. Min Act: -0.1700
Data Index: 824498 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.5967. Min Act: -0.1700
Data Index: 965466 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.6128. Min Act: -0.1700
Data Index: 953545 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7729. Min Range: -2.7729
Max Act: 2.5967. Min Act: -0.1700
Data Index: 32414 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19