Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 39 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.6032. Min Act: -0.1700
Data Index: 1039750 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.5871. Min Act: -0.1700
Data Index: 1195752 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.5225. Min Act: -0.1700
Data Index: 236499 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.5225. Min Act: -0.1700
Data Index: 1029598 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4902. Min Act: -0.1700
Data Index: 1261506 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4902. Min Act: -0.1700
Data Index: 96354 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4902. Min Act: -0.1700
Data Index: 1178240 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4415. Min Act: -0.1700
Data Index: 359610 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4577. Min Act: -0.1700
Data Index: 1265296 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4415. Min Act: -0.1700
Data Index: 1284611 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4415. Min Act: -0.1700
Data Index: 77330 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4577. Min Act: -0.1700
Data Index: 853654 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4577. Min Act: -0.1700
Data Index: 42402 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4415. Min Act: -0.1700
Data Index: 842972 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4252. Min Act: -0.1700
Data Index: 623179 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4415. Min Act: -0.1700
Data Index: 760837 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4089. Min Act: -0.1700
Data Index: 274551 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.3926. Min Act: -0.1700
Data Index: 525076 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.4089. Min Act: -0.1700
Data Index: 503634 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6032. Min Range: -2.6032
Max Act: 2.3926. Min Act: -0.1700
Data Index: 504591 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19