Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1654 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1570. Min Range: -6.1570
Max Act: 6.1258. Min Act: -0.1700
Data Index: 356237 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1570. Min Range: -6.1570
Max Act: 6.1570. Min Act: -0.1700
Data Index: 938434 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1570. Min Range: -6.1570
Max Act: 6.0633. Min Act: -0.1700
Data Index: 108759 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.9070. Min Act: -0.1700
Data Index: 884557 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.9695. Min Act: -0.1700
Data Index: 1412070 (Python Code)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.8133. Min Act: -0.1700
Data Index: 751001 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.6258. Min Act: -0.1700
Data Index: 713727 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 113387 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5633. Min Act: -0.1700
Data Index: 495329 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5633. Min Act: -0.1700
Data Index: 339671 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5945. Min Act: -0.1700
Data Index: 1145462 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 829288 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 450128 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5008. Min Act: -0.1700
Data Index: 460409 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.5008. Min Act: -0.1700
Data Index: 228378 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.4070. Min Act: -0.1700
Data Index: 574768 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.4383. Min Act: -0.1700
Data Index: 570244 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.4383. Min Act: -0.1700
Data Index: 1358689 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.4383. Min Act: -0.1700
Data Index: 1241625 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1570. Min Range: -6.1570
Max Act: 5.4070. Min Act: -0.1700
Data Index: 761149 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19