Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.4737. Min Act: -0.1700
Data Index: 1524815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.4737. Min Act: -0.1700
Data Index: 4779290 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0987. Min Act: -0.1700
Data Index: 4832857 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0674. Min Act: -0.1700
Data Index: 2101077 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0674. Min Act: -0.1700
Data Index: 4809325 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0362. Min Act: -0.1700
Data Index: 1353639 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0674. Min Act: -0.1700
Data Index: 182248 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0049. Min Act: -0.1700
Data Index: 7779380 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0049. Min Act: -0.1700
Data Index: 5838456 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9737. Min Act: -0.1700
Data Index: 5778052 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9737. Min Act: -0.1700
Data Index: 5192160 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0049. Min Act: -0.1700
Data Index: 6520189 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.0049. Min Act: -0.1700
Data Index: 8418906 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9424. Min Act: -0.1700
Data Index: 3754416 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9737. Min Act: -0.1700
Data Index: 670151 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9111. Min Act: -0.1700
Data Index: 1668108 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9111. Min Act: -0.1700
Data Index: 358779 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9111. Min Act: -0.1700
Data Index: 2691394 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9111. Min Act: -0.1700
Data Index: 7017800 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4737. Min Range: -4.4737
Max Act: 3.9111. Min Act: -0.1700
Data Index: 4917238 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19