Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1775 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9943. Min Act: -0.1700
Data Index: 1031136 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9626. Min Act: -0.1700
Data Index: 1390369 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9626. Min Act: -0.1700
Data Index: 842082 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9468. Min Act: -0.1700
Data Index: 1244500 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9468. Min Act: -0.1700
Data Index: 90142 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9626. Min Act: -0.1700
Data Index: 1403806 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9310. Min Act: -0.1700
Data Index: 440587 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9310. Min Act: -0.1700
Data Index: 1428080 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 1608960 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9468. Min Act: -0.1700
Data Index: 1498804 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9310. Min Act: -0.1700
Data Index: 1028922 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 1376938 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 1375633 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 1515947 (Python Code)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 773879 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 24832 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 88980 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 456432 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.9151. Min Act: -0.1700
Data Index: 1419277 (Python Code)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9943. Min Range: -2.9943
Max Act: 2.8992. Min Act: -0.1700
Data Index: 1461122 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19