Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0244. Min Range: -8.0244
Max Act: 8.0244. Min Act: -0.1700
Data Index: 264937 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.9306. Min Act: -0.1700
Data Index: 3741841 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.9306. Min Act: -0.1700
Data Index: 390164 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.7119. Min Act: -0.1700
Data Index: 6576760 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.6494. Min Act: -0.1700
Data Index: 4582962 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.6494. Min Act: -0.1700
Data Index: 5842904 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.6181. Min Act: -0.1700
Data Index: 7113075 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.6181. Min Act: -0.1700
Data Index: 1620033 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5556. Min Act: -0.1700
Data Index: 449713 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5556. Min Act: -0.1700
Data Index: 3970580 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5556. Min Act: -0.1700
Data Index: 6714092 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5869. Min Act: -0.1700
Data Index: 5700717 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5244. Min Act: -0.1700
Data Index: 4556551 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4931. Min Act: -0.1700
Data Index: 5236683 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4619. Min Act: -0.1700
Data Index: 7191509 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5244. Min Act: -0.1700
Data Index: 6246140 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4931. Min Act: -0.1700
Data Index: 7996395 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4619. Min Act: -0.1700
Data Index: 752498 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4619. Min Act: -0.1700
Data Index: 2078682 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4931. Min Act: -0.1700
Data Index: 2400108 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19