Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1871 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.1624. Min Act: -0.1700
Data Index: 633828 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0994. Min Act: -0.1700
Data Index: 1156827 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0836. Min Act: -0.1700
Data Index: 1024809 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0521. Min Act: -0.1700
Data Index: 584267 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0363. Min Act: -0.1700
Data Index: 165856 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0363. Min Act: -0.1700
Data Index: 910796 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0521. Min Act: -0.1700
Data Index: 103847 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0363. Min Act: -0.1700
Data Index: 713542 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0205. Min Act: -0.1700
Data Index: 816213 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0363. Min Act: -0.1700
Data Index: 684680 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0047. Min Act: -0.1700
Data Index: 567225 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0047. Min Act: -0.1700
Data Index: 357980 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1624. Min Range: -3.1624
Max Act: 3.0047. Min Act: -0.1700
Data Index: 1197295 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9889. Min Act: -0.1700
Data Index: 420034 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9889. Min Act: -0.1700
Data Index: 409327 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9889. Min Act: -0.1700
Data Index: 640434 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9730. Min Act: -0.1700
Data Index: 423320 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9730. Min Act: -0.1700
Data Index: 1174364 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9730. Min Act: -0.1700
Data Index: 1228046 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1624. Min Range: -3.1624
Max Act: 2.9730. Min Act: -0.1700
Data Index: 491876 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19