Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1238 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.9145. Min Act: -0.1700
Data Index: 177460 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.5083. Min Act: -0.1700
Data Index: 808700 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.3833. Min Act: -0.1700
Data Index: 562791 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.3207. Min Act: -0.1700
Data Index: 904227 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2895. Min Act: -0.1700
Data Index: 1559352 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.3520. Min Act: -0.1700
Data Index: 147991 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.3207. Min Act: -0.1700
Data Index: 205947 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2895. Min Act: -0.1700
Data Index: 1347299 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2895. Min Act: -0.1700
Data Index: 1044136 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2582. Min Act: -0.1700
Data Index: 305196 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2270. Min Act: -0.1700
Data Index: 1422498 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2582. Min Act: -0.1700
Data Index: 1612379 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2270. Min Act: -0.1700
Data Index: 320589 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2270. Min Act: -0.1700
Data Index: 64186 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.1957. Min Act: -0.1700
Data Index: 459185 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.2270. Min Act: -0.1700
Data Index: 444907 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.1957. Min Act: -0.1700
Data Index: 630243 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.1957. Min Act: -0.1700
Data Index: 620633 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.1957. Min Act: -0.1700
Data Index: 722090 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9145. Min Range: -4.9145
Max Act: 4.1957. Min Act: -0.1700
Data Index: 1307461 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19