Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1012 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.8220. Min Act: -0.1700
Data Index: 7659791 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.6970. Min Act: -0.1700
Data Index: 6653198 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.6970. Min Act: -0.1700
Data Index: 3894029 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.6970. Min Act: -0.1700
Data Index: 2439933 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.5095. Min Act: -0.1700
Data Index: 6851068 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.5095. Min Act: -0.1700
Data Index: 1017453 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.4470. Min Act: -0.1700
Data Index: 8295006 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.4470. Min Act: -0.1700
Data Index: 2467504 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.4157. Min Act: -0.1700
Data Index: 8034632 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.4157. Min Act: -0.1700
Data Index: 3258143 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3845. Min Act: -0.1700
Data Index: 4517255 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3845. Min Act: -0.1700
Data Index: 4533116 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3845. Min Act: -0.1700
Data Index: 1266086 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3845. Min Act: -0.1700
Data Index: 1596815 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3532. Min Act: -0.1700
Data Index: 2405613 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3532. Min Act: -0.1700
Data Index: 3087486 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3532. Min Act: -0.1700
Data Index: 7808671 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3220. Min Act: -0.1700
Data Index: 2294592 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3220. Min Act: -0.1700
Data Index: 4649871 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8220. Min Range: -7.8220
Max Act: 7.3220. Min Act: -0.1700
Data Index: 2858833 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19