Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6272 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.9292. Min Act: -0.1700
Data Index: 4877687 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.8980. Min Act: -0.1700
Data Index: 6472209 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.8980. Min Act: -0.1700
Data Index: 5646173 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.8980. Min Act: -0.1700
Data Index: 271111 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.8667. Min Act: -0.1700
Data Index: 8143013 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.8198. Min Act: -0.1700
Data Index: 3767539 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7885. Min Act: -0.1700
Data Index: 927333 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7729. Min Act: -0.1700
Data Index: 400144 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7729. Min Act: -0.1700
Data Index: 5392595 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7572. Min Act: -0.1700
Data Index: 4129688 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7572. Min Act: -0.1700
Data Index: 5054716 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4349326 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7572. Min Act: -0.1700
Data Index: 5096753 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7416. Min Act: -0.1700
Data Index: 84122 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4462691 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7416. Min Act: -0.1700
Data Index: 3519418 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7259. Min Act: -0.1700
Data Index: 63201 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7259. Min Act: -0.1700
Data Index: 5743071 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7103. Min Act: -0.1700
Data Index: 886996 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9292. Min Range: -3.9292
Max Act: 3.7259. Min Act: -0.1700
Data Index: 2006606 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19