Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1202 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.1715. Min Act: -0.1699
Data Index: 887417 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.0777. Min Act: -0.1700
Data Index: 800286 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.1090. Min Act: -0.1700
Data Index: 1305549 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.0777. Min Act: -0.1700
Data Index: 913396 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.0464. Min Act: -0.1700
Data Index: 844417 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.0152. Min Act: -0.1700
Data Index: 1179816 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9839. Min Act: -0.1700
Data Index: 568496 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9839. Min Act: -0.1700
Data Index: 338205 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9214. Min Act: -0.1700
Data Index: 1316075 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9214. Min Act: -0.1700
Data Index: 623480 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9526. Min Act: -0.1700
Data Index: 516996 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9839. Min Act: -0.1700
Data Index: 489141 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1715. Min Range: -4.1715
Max Act: 4.0464. Min Act: -0.1700
Data Index: 813556 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9526. Min Act: -0.1700
Data Index: 975748 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9526. Min Act: -0.1700
Data Index: 1192089 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9214. Min Act: -0.1700
Data Index: 954050 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.8901. Min Act: -0.1700
Data Index: 1000130 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.8901. Min Act: -0.1700
Data Index: 1002001 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.9214. Min Act: -0.1700
Data Index: 1038632 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1715. Min Range: -4.1715
Max Act: 3.8901. Min Act: -0.1700
Data Index: 360308 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19