Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 849 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8853. Min Act: -0.1700
Data Index: 629355 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8853. Min Act: -0.1700
Data Index: 218984 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8853. Min Act: -0.1700
Data Index: 669202 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8535. Min Act: -0.1700
Data Index: 40266 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8376. Min Act: -0.1700
Data Index: 188908 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8535. Min Act: -0.1700
Data Index: 86111 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8535. Min Act: -0.1700
Data Index: 887555 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8535. Min Act: -0.1700
Data Index: 1013434 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 320916 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8376. Min Act: -0.1700
Data Index: 14942 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8376. Min Act: -0.1700
Data Index: 818181 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8535. Min Act: -0.1700
Data Index: 376007 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 1337394 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 131213 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 516487 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8058. Min Act: -0.1700
Data Index: 1098340 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 535848 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8217. Min Act: -0.1700
Data Index: 377752 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8058. Min Act: -0.1700
Data Index: 362334 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8853. Min Range: -2.8853
Max Act: 2.8058. Min Act: -0.1700
Data Index: 569635 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19