Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1372 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.9100. Min Act: -0.1700
Data Index: 346692 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.8306. Min Act: -0.1700
Data Index: 392038 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.8306. Min Act: -0.1700
Data Index: 117990 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.7030. Min Act: -0.1700
Data Index: 600038 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6870. Min Act: -0.1700
Data Index: 1586925 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6870. Min Act: -0.1700
Data Index: 742674 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6870. Min Act: -0.1700
Data Index: 1044685 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6870. Min Act: -0.1700
Data Index: 1060147 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6710. Min Act: -0.1700
Data Index: 912260 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6710. Min Act: -0.1700
Data Index: 393636 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6710. Min Act: -0.1700
Data Index: 319687 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6228. Min Act: -0.1700
Data Index: 371251 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6549. Min Act: -0.1700
Data Index: 590258 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6549. Min Act: -0.1700
Data Index: 948717 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6549. Min Act: -0.1700
Data Index: 1259621 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6549. Min Act: -0.1700
Data Index: 1180767 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6389. Min Act: -0.1700
Data Index: 1092981 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6389. Min Act: -0.1700
Data Index: 879694 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6389. Min Act: -0.1700
Data Index: 520907 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9100. Min Range: -2.9100
Max Act: 2.6389. Min Act: -0.1700
Data Index: 995257 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19