Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5555 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4113. Min Range: -7.4113
Max Act: 7.4113. Min Act: -0.1700
Data Index: 6823022 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.7238. Min Act: -0.1700
Data Index: 7079888 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.5676. Min Act: -0.1700
Data Index: 181919 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.5051. Min Act: -0.1700
Data Index: 2970739 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.4426. Min Act: -0.1700
Data Index: 738401 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.3176. Min Act: -0.1700
Data Index: 2210912 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.2238. Min Act: -0.1700
Data Index: 4018176 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.1926. Min Act: -0.1700
Data Index: 4992273 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.1613. Min Act: -0.1700
Data Index: 6398853 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.1613. Min Act: -0.1700
Data Index: 6931360 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0988. Min Act: -0.1700
Data Index: 1262094 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.1301. Min Act: -0.1700
Data Index: 1723045 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.1301. Min Act: -0.1700
Data Index: 6029438 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0988. Min Act: -0.1700
Data Index: 2233033 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0676. Min Act: -0.1700
Data Index: 4115667 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0051. Min Act: -0.1700
Data Index: 1785257 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1882132 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0051. Min Act: -0.1700
Data Index: 8732497 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4113. Min Range: -7.4113
Max Act: 6.0051. Min Act: -0.1700
Data Index: 475350 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4113. Min Range: -7.4113
Max Act: 5.9426. Min Act: -0.1700
Data Index: 6299005 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19