Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 115 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.8712. Min Act: -0.1700
Data Index: 543918 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.8712. Min Act: -0.1700
Data Index: 302265 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.8235. Min Act: -0.1700
Data Index: 1277576 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7916. Min Act: -0.1700
Data Index: 607774 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7916. Min Act: -0.1700
Data Index: 585540 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7916. Min Act: -0.1700
Data Index: 439050 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7757. Min Act: -0.1700
Data Index: 945713 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 591134 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 1049780 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 150197 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 401806 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 397263 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7278. Min Act: -0.1700
Data Index: 700481 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7438. Min Act: -0.1700
Data Index: 529147 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7278. Min Act: -0.1700
Data Index: 1194003 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7278. Min Act: -0.1700
Data Index: 1060946 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7438. Min Act: -0.1700
Data Index: 114390 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7438. Min Act: -0.1700
Data Index: 998614 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7278. Min Act: -0.1700
Data Index: 460510 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8712. Min Range: -2.8712
Max Act: 2.7597. Min Act: -0.1700
Data Index: 391025 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19