Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1428 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.1619. Min Act: -0.1700
Data Index: 39331 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.2245. Min Act: -0.1700
Data Index: 717880 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.1307. Min Act: -0.1700
Data Index: 885361 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0994. Min Act: -0.1700
Data Index: 923784 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.1307. Min Act: -0.1700
Data Index: 265718 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0994. Min Act: -0.1700
Data Index: 1106278 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.1619. Min Act: -0.1700
Data Index: 316724 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0369. Min Act: -0.1700
Data Index: 297246 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0056. Min Act: -0.1700
Data Index: 950129 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 31944 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0056. Min Act: -0.1700
Data Index: 296817 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0369. Min Act: -0.1700
Data Index: 143686 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 53851 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 568024 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0369. Min Act: -0.1700
Data Index: 593376 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 859723 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 193937 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0056. Min Act: -0.1700
Data Index: 640518 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0682. Min Act: -0.1700
Data Index: 409879 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2245. Min Range: -4.2245
Max Act: 4.0369. Min Act: -0.1700
Data Index: 226462 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19