Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1764 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.6978. Min Act: -0.1700
Data Index: 489302 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.6666. Min Act: -0.1700
Data Index: 1224445 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.6353. Min Act: -0.1700
Data Index: 248065 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.6041. Min Act: -0.1700
Data Index: 426936 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.5103. Min Act: -0.1700
Data Index: 497648 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4791. Min Act: -0.1700
Data Index: 86032 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.5103. Min Act: -0.1700
Data Index: 204023 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4791. Min Act: -0.1700
Data Index: 207327 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4791. Min Act: -0.1700
Data Index: 703115 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4478. Min Act: -0.1700
Data Index: 958808 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4478. Min Act: -0.1700
Data Index: 215787 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4166. Min Act: -0.1700
Data Index: 1021740 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4166. Min Act: -0.1700
Data Index: 1096774 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4478. Min Act: -0.1700
Data Index: 740253 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.3541. Min Act: -0.1700
Data Index: 295856 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.4166. Min Act: -0.1700
Data Index: 66447 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.3853. Min Act: -0.1700
Data Index: 346077 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.3853. Min Act: -0.1700
Data Index: 160558 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.3541. Min Act: -0.1700
Data Index: 283347 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6978. Min Range: -4.6978
Max Act: 4.3853. Min Act: -0.1700
Data Index: 1070049 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19