Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1247 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1545. Min Range: -4.1545
Max Act: 4.1545. Min Act: -0.1700
Data Index: 1198585 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1545. Min Range: -4.1545
Max Act: 4.0919. Min Act: -0.1700
Data Index: 364654 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1545. Min Range: -4.1545
Max Act: 4.0607. Min Act: -0.1700
Data Index: 1330539 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1545. Min Range: -4.1545
Max Act: 4.0294. Min Act: -0.1700
Data Index: 662915 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1545. Min Range: -4.1545
Max Act: 4.0294. Min Act: -0.1700
Data Index: 981446 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9982. Min Act: -0.1700
Data Index: 162495 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9356. Min Act: -0.1700
Data Index: 550540 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 571831 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 349145 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 509959 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.8731. Min Act: -0.1700
Data Index: 512324 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 719851 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 436836 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 783701 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 67317 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.9043. Min Act: -0.1700
Data Index: 505691 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.8731. Min Act: -0.1700
Data Index: 977747 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.8731. Min Act: -0.1700
Data Index: 831528 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.8731. Min Act: -0.1700
Data Index: 338568 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1545. Min Range: -4.1545
Max Act: 3.8731. Min Act: -0.1700
Data Index: 166295 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19