Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 123 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.5830. Min Act: -0.1700
Data Index: 369105 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.4580. Min Act: -0.1700
Data Index: 1311163 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3643. Min Act: -0.1700
Data Index: 512071 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.4268. Min Act: -0.1700
Data Index: 314307 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.4268. Min Act: -0.1700
Data Index: 1244551 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3955. Min Act: -0.1700
Data Index: 1299977 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3955. Min Act: -0.1700
Data Index: 883396 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.4268. Min Act: -0.1700
Data Index: 900591 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3643. Min Act: -0.1700
Data Index: 594355 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3643. Min Act: -0.1700
Data Index: 772608 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3643. Min Act: -0.1700
Data Index: 18041 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3018. Min Act: -0.1700
Data Index: 957521 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3018. Min Act: -0.1700
Data Index: 187371 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3018. Min Act: -0.1700
Data Index: 832895 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.2705. Min Act: -0.1700
Data Index: 620629 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3018. Min Act: -0.1700
Data Index: 1152760 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.2392. Min Act: -0.1700
Data Index: 535181 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.2392. Min Act: -0.1700
Data Index: 872875 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.3018. Min Act: -0.1700
Data Index: 619739 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5830. Min Range: -4.5830
Max Act: 4.2705. Min Act: -0.1700
Data Index: 560292 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19