Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2032 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.9724. Min Act: -0.1700
Data Index: 450489 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.9091. Min Act: -0.1700
Data Index: 981330 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.8615. Min Act: -0.1700
Data Index: 974741 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.8297. Min Act: -0.1700
Data Index: 1252497 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.8138. Min Act: -0.1700
Data Index: 453409 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.8138. Min Act: -0.1700
Data Index: 855472 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7978. Min Act: -0.1700
Data Index: 1218781 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7978. Min Act: -0.1700
Data Index: 1103019 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7819. Min Act: -0.1700
Data Index: 793045 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7819. Min Act: -0.1700
Data Index: 874270 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7819. Min Act: -0.1700
Data Index: 293553 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7660. Min Act: -0.1700
Data Index: 638487 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7660. Min Act: -0.1700
Data Index: 1143289 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7021. Min Act: -0.1700
Data Index: 434806 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7500. Min Act: -0.1700
Data Index: 108775 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7340. Min Act: -0.1700
Data Index: 277909 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7500. Min Act: -0.1700
Data Index: 1144342 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7500. Min Act: -0.1700
Data Index: 594582 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7180. Min Act: -0.1700
Data Index: 344912 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9724. Min Range: -2.9724
Max Act: 2.7500. Min Act: -0.1700
Data Index: 281070 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19