Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.3926. Min Act: -0.1700
Data Index: 3094658 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.1738. Min Act: -0.1700
Data Index: 4857095 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.1113. Min Act: -0.1700
Data Index: 2263907 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.1426. Min Act: -0.1700
Data Index: 716946 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.0801. Min Act: -0.1700
Data Index: 7957569 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.0488. Min Act: -0.1700
Data Index: 223589 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.0801. Min Act: -0.1700
Data Index: 4553153 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.0176. Min Act: -0.1700
Data Index: 2607029 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.0176. Min Act: -0.1700
Data Index: 665084 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9863. Min Act: -0.1700
Data Index: 4406854 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9238. Min Act: -0.1700
Data Index: 3322071 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9551. Min Act: -0.1700
Data Index: 5837343 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9551. Min Act: -0.1700
Data Index: 4393726 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4101353 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9238. Min Act: -0.1700
Data Index: 5198773 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.9238. Min Act: -0.1700
Data Index: 5570776 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.8926. Min Act: -0.1700
Data Index: 5361586 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.8926. Min Act: -0.1700
Data Index: 3650701 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.8613. Min Act: -0.1700
Data Index: 1634721 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.8926. Min Act: -0.1700
Data Index: 1104807 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19