Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 140 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.9008. Min Act: -0.1700
Data Index: 263683 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.8532. Min Act: -0.1700
Data Index: 414225 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.8373. Min Act: -0.1700
Data Index: 955697 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7896. Min Act: -0.1700
Data Index: 952240 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7896. Min Act: -0.1700
Data Index: 381880 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7736. Min Act: -0.1700
Data Index: 864908 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7736. Min Act: -0.1700
Data Index: 993856 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7577. Min Act: -0.1700
Data Index: 971629 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7257. Min Act: -0.1700
Data Index: 1412786 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7417. Min Act: -0.1700
Data Index: 94399 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7577. Min Act: -0.1700
Data Index: 1080123 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7097. Min Act: -0.1700
Data Index: 748064 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7417. Min Act: -0.1700
Data Index: 182623 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7257. Min Act: -0.1700
Data Index: 569744 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.7257. Min Act: -0.1700
Data Index: 916619 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.6937. Min Act: -0.1700
Data Index: 457577 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.6937. Min Act: -0.1700
Data Index: 585849 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.6777. Min Act: -0.1700
Data Index: 508314 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.6617. Min Act: -0.1700
Data Index: 8519 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9008. Min Range: -2.9008
Max Act: 2.6777. Min Act: -0.1700
Data Index: 1508665 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19