Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2029 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5661. Min Act: -0.1700
Data Index: 1273638 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5973. Min Act: -0.1700
Data Index: 706956 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5973. Min Act: -0.1700
Data Index: 40229 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5348. Min Act: -0.1700
Data Index: 861301 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5348. Min Act: -0.1700
Data Index: 998797 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5348. Min Act: -0.1700
Data Index: 1339433 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5661. Min Act: -0.1700
Data Index: 797723 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5036. Min Act: -0.1700
Data Index: 1325012 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5036. Min Act: -0.1700
Data Index: 344378 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4098. Min Act: -0.1700
Data Index: 1310579 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.5036. Min Act: -0.1700
Data Index: 49563 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4098. Min Act: -0.1700
Data Index: 807718 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4098. Min Act: -0.1700
Data Index: 431831 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4723. Min Act: -0.1700
Data Index: 371393 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4411. Min Act: -0.1700
Data Index: 897220 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4411. Min Act: -0.1700
Data Index: 144825 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4723. Min Act: -0.1700
Data Index: 670623 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.3786. Min Act: -0.1700
Data Index: 804893 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.3786. Min Act: -0.1700
Data Index: 271136 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5973. Min Range: -4.5973
Max Act: 4.4098. Min Act: -0.1700
Data Index: 521977 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19