Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 588 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1039. Min Range: -4.1039
Max Act: 4.1039. Min Act: -0.1700
Data Index: 775039 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1039. Min Range: -4.1039
Max Act: 4.0101. Min Act: -0.1700
Data Index: 696029 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1039. Min Range: -4.1039
Max Act: 4.0101. Min Act: -0.1700
Data Index: 1294513 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9789. Min Act: -0.1700
Data Index: 593801 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9789. Min Act: -0.1700
Data Index: 572411 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9476. Min Act: -0.1700
Data Index: 1204235 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9476. Min Act: -0.1700
Data Index: 514413 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9476. Min Act: -0.1700
Data Index: 281078 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.9163. Min Act: -0.1700
Data Index: 41731 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8850. Min Act: -0.1700
Data Index: 269805 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8538. Min Act: -0.1700
Data Index: 301616 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8538. Min Act: -0.1700
Data Index: 882884 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8850. Min Act: -0.1700
Data Index: 744832 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8850. Min Act: -0.1700
Data Index: 886610 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.7912. Min Act: -0.1700
Data Index: 1213305 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8225. Min Act: -0.1700
Data Index: 1103856 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.7912. Min Act: -0.1700
Data Index: 663986 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.8538. Min Act: -0.1700
Data Index: 441496 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.7912. Min Act: -0.1700
Data Index: 726153 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1039. Min Range: -4.1039
Max Act: 3.7912. Min Act: -0.1700
Data Index: 289443 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19