Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1549 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0670. Min Range: -3.0670
Max Act: 3.0670. Min Act: -0.1700
Data Index: 1375545 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.2390. Min Act: -0.1700
Data Index: 269141 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.2224. Min Act: -0.1700
Data Index: 705899 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1893. Min Act: -0.1700
Data Index: 564018 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1893. Min Act: -0.1698
Data Index: 277932 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1810. Min Act: -0.1699
Data Index: 504642 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1727. Min Act: -0.1700
Data Index: 822777 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1560. Min Act: -0.1700
Data Index: 849684 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1394. Min Act: -0.1700
Data Index: 619447 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1477. Min Act: -0.1700
Data Index: 493683 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1394. Min Act: -0.1699
Data Index: 1263380 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1477. Min Act: -0.1699
Data Index: 1166253 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1394. Min Act: -0.1700
Data Index: 713697 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1394. Min Act: -0.1700
Data Index: 203526 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1227. Min Act: -0.1700
Data Index: 366097 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1310. Min Act: -0.1700
Data Index: 1421588 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1227. Min Act: -0.1209
Data Index: 1440449 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1143. Min Act: -0.1698
Data Index: 1139021 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1060. Min Act: -0.1700
Data Index: 793872 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0670. Min Range: -3.0670
Max Act: 2.1227. Min Act: -0.1700
Data Index: 1219645 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19