Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4721 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5634. Min Range: -6.5634
Max Act: 6.5634. Min Act: -0.1700
Data Index: 1772291 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5634. Min Range: -6.5634
Max Act: 6.0321. Min Act: -0.1700
Data Index: 8193712 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.8134. Min Act: -0.1700
Data Index: 450058 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.8134. Min Act: -0.1700
Data Index: 6078201 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.7821. Min Act: -0.1700
Data Index: 532618 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4671698 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6884. Min Act: -0.1700
Data Index: 3765966 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6884. Min Act: -0.1700
Data Index: 5153078 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6571. Min Act: -0.1700
Data Index: 2755794 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6571. Min Act: -0.1700
Data Index: 4129774 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6259. Min Act: -0.1700
Data Index: 8089436 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.6259. Min Act: -0.1700
Data Index: 8709715 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5634. Min Act: -0.1700
Data Index: 5840598 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5634. Min Act: -0.1700
Data Index: 318168 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5634. Min Act: -0.1700
Data Index: 4303923 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5321. Min Act: -0.1700
Data Index: 6230271 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5321. Min Act: -0.1700
Data Index: 2697384 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5815612 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.5009. Min Act: -0.1700
Data Index: 8800674 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5634. Min Range: -6.5634
Max Act: 5.4696. Min Act: -0.1700
Data Index: 7477739 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19