Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 283 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.7577. Min Act: -0.1700
Data Index: 871686 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.7257. Min Act: -0.1700
Data Index: 1341403 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.6457. Min Act: -0.1700
Data Index: 517596 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5974. Min Act: -0.1700
Data Index: 714607 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5974. Min Act: -0.1700
Data Index: 778866 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5974. Min Act: -0.1700
Data Index: 1225961 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5974. Min Act: -0.1700
Data Index: 1184747 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 347280 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 259845 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 40447 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 617503 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 679864 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 253390 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 1108431 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 15097 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 236620 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 409460 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 839777 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5652. Min Act: -0.1700
Data Index: 482656 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5813. Min Act: -0.1700
Data Index: 1255769 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19