Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 58 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.2723. Min Act: -0.1700
Data Index: 1534324 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1402424 (Python Code)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.1785. Min Act: -0.1700
Data Index: 1596604 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.1160. Min Act: -0.1700
Data Index: 1497550 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0691. Min Act: -0.1700
Data Index: 1574688 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0535. Min Act: -0.1700
Data Index: 1478426 (Python Code)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0691. Min Act: -0.1700
Data Index: 1543324 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0378. Min Act: -0.1700
Data Index: 1513359 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0378. Min Act: -0.1700
Data Index: 1376403 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9910. Min Act: -0.1700
Data Index: 1418120 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1628775 (Python Code)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0066. Min Act: -0.1700
Data Index: 1395271 (Python Code)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0066. Min Act: -0.1700
Data Index: 1391642 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9597. Min Act: -0.1700
Data Index: 1451010 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2723. Min Range: -4.2723
Max Act: 4.0066. Min Act: -0.1700
Data Index: 1397912 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1537869 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9753. Min Act: -0.1700
Data Index: 1592526 (Python Code)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9910. Min Act: -0.1700
Data Index: 1465579 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1603981 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2723. Min Range: -4.2723
Max Act: 3.9597. Min Act: -0.1700
Data Index: 1622798 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19