Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1831 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.6581. Min Act: -0.1700
Data Index: 849352 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.6260. Min Act: -0.1700
Data Index: 1063905 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.6099. Min Act: -0.1700
Data Index: 687239 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5938. Min Act: -0.1700
Data Index: 1262730 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5777. Min Act: -0.1700
Data Index: 513970 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5616. Min Act: -0.1700
Data Index: 808807 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5455. Min Act: -0.1700
Data Index: 1374869 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5293. Min Act: -0.1700
Data Index: 690939 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5293. Min Act: -0.1700
Data Index: 804220 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.5131. Min Act: -0.1700
Data Index: 1133060 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4970. Min Act: -0.1700
Data Index: 864621 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4807. Min Act: -0.1700
Data Index: 1267330 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4807. Min Act: -0.1700
Data Index: 548384 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4645. Min Act: -0.1700
Data Index: 485069 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4645. Min Act: -0.1700
Data Index: 856456 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4645. Min Act: -0.1700
Data Index: 390058 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4807. Min Act: -0.1700
Data Index: 41176 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4807. Min Act: -0.1700
Data Index: 303878 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4807. Min Act: -0.1700
Data Index: 926481 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6581. Min Range: -2.6581
Max Act: 2.4645. Min Act: -0.1700
Data Index: 315950 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19