Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1019 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.4509. Min Act: -0.1700
Data Index: 1266492 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.4346. Min Act: -0.1700
Data Index: 150823 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.4509. Min Act: -0.1700
Data Index: 285692 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.4346. Min Act: -0.1700
Data Index: 1016966 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3694. Min Act: -0.1700
Data Index: 377043 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3694. Min Act: -0.1700
Data Index: 1032243 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3367. Min Act: -0.1700
Data Index: 1654478 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3367. Min Act: -0.1700
Data Index: 727326 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3367. Min Act: -0.1700
Data Index: 15896 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3203. Min Act: -0.1700
Data Index: 384878 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3203. Min Act: -0.1700
Data Index: 938528 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 1264882 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 687914 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 245185 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 287411 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 300513 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.3038. Min Act: -0.1700
Data Index: 1509418 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.2874. Min Act: -0.1700
Data Index: 1100649 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.2874. Min Act: -0.1700
Data Index: 329686 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4509. Min Range: -2.4509
Max Act: 2.2544. Min Act: -0.1700
Data Index: 883274 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19