Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 220 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.9078. Min Act: -0.1700
Data Index: 207293 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.9078. Min Act: -0.1700
Data Index: 672508 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6890. Min Act: -0.1700
Data Index: 1290509 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.8453. Min Act: -0.1700
Data Index: 387067 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6265. Min Act: -0.1700
Data Index: 31814 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5953. Min Act: -0.1700
Data Index: 152612 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.7515. Min Act: -0.1700
Data Index: 1135350 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6578. Min Act: -0.1700
Data Index: 1557689 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5953. Min Act: -0.1700
Data Index: 1049010 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6578. Min Act: -0.1700
Data Index: 1244038 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5328. Min Act: -0.1700
Data Index: 659635 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6265. Min Act: -0.1700
Data Index: 389109 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5640. Min Act: -0.1700
Data Index: 1246982 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.4703. Min Act: -0.1700
Data Index: 1138649 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.6578. Min Act: -0.1700
Data Index: 680105 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5640. Min Act: -0.1700
Data Index: 1623096 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.3765. Min Act: -0.1700
Data Index: 699372 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5015. Min Act: -0.1700
Data Index: 491619 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.4703. Min Act: -0.1700
Data Index: 170571 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9078. Min Range: -4.9078
Max Act: 4.5328. Min Act: -0.1700
Data Index: 331285 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19