Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 210 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9904. Min Act: -0.1700
Data Index: 911743 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9746. Min Act: -0.1700
Data Index: 1004792 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9904. Min Act: -0.1700
Data Index: 1301785 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9746. Min Act: -0.1700
Data Index: 755710 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1234871 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1015132 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9587. Min Act: -0.1700
Data Index: 323801 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9587. Min Act: -0.1700
Data Index: 403537 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9271. Min Act: -0.1700
Data Index: 311159 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 412596 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9271. Min Act: -0.1700
Data Index: 431763 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 734595 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1313375 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 646655 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 557212 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1025002 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9271. Min Act: -0.1700
Data Index: 195104 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9271. Min Act: -0.1700
Data Index: 912346 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9112. Min Act: -0.1700
Data Index: 330909 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9904. Min Range: -2.9904
Max Act: 2.9271. Min Act: -0.1700
Data Index: 278817 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19