Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.8235. Min Act: -0.1700
Data Index: 58159 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.5735. Min Act: -0.1700
Data Index: 7935611 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.2610. Min Act: -0.1700
Data Index: 2005981 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.1985. Min Act: -0.1700
Data Index: 6472945 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.0110. Min Act: -0.1700
Data Index: 5688580 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8235. Min Range: -6.8235
Max Act: 6.0110. Min Act: -0.1700
Data Index: 7886530 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.9798. Min Act: -0.1700
Data Index: 2514601 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8860. Min Act: -0.1700
Data Index: 5257168 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8860. Min Act: -0.1700
Data Index: 8552325 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8860. Min Act: -0.1700
Data Index: 6818337 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3693388 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 525546 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 7324563 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.8548. Min Act: -0.1700
Data Index: 1671492 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.7610. Min Act: -0.1700
Data Index: 8281309 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.7610. Min Act: -0.1700
Data Index: 5442243 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.7298. Min Act: -0.1700
Data Index: 116687 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5436604 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.7298. Min Act: -0.1700
Data Index: 998652 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8235. Min Range: -6.8235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 330592 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19