Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.9328. Min Act: -0.1700
Data Index: 966223 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.9645. Min Act: -0.1700
Data Index: 132369 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.9011. Min Act: -0.1700
Data Index: 3903 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8376. Min Act: -0.1700
Data Index: 328189 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8535. Min Act: -0.1700
Data Index: 289348 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8058. Min Act: -0.1700
Data Index: 793795 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8535. Min Act: -0.1700
Data Index: 269056 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8217. Min Act: -0.1700
Data Index: 327851 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7898. Min Act: -0.1700
Data Index: 1161012 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8058. Min Act: -0.1700
Data Index: 242339 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.8058. Min Act: -0.1700
Data Index: 1146876 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7739. Min Act: -0.1700
Data Index: 903027 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7898. Min Act: -0.1700
Data Index: 834085 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7739. Min Act: -0.1700
Data Index: 624629 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7579. Min Act: -0.1700
Data Index: 146220 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7739. Min Act: -0.1700
Data Index: 176409 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7579. Min Act: -0.1700
Data Index: 1288968 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7420. Min Act: -0.1700
Data Index: 233282 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7420. Min Act: -0.1700
Data Index: 181945 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9645. Min Range: -2.9645
Max Act: 2.7579. Min Act: -0.1700
Data Index: 1018162 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19