Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4607 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.4884. Min Act: -0.1700
Data Index: 6295872 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.0821. Min Act: -0.1700
Data Index: 5182183 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.0821. Min Act: -0.1700
Data Index: 6651783 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.0509. Min Act: -0.1700
Data Index: 2139797 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.0821. Min Act: -0.1700
Data Index: 3078682 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4884. Min Range: -4.4884
Max Act: 4.0509. Min Act: -0.1700
Data Index: 6747276 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9571. Min Act: -0.1700
Data Index: 4831392 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9884. Min Act: -0.1700
Data Index: 1714781 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6838171 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6757311 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6757299 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9258. Min Act: -0.1700
Data Index: 4858567 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9258. Min Act: -0.1700
Data Index: 34967 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9258. Min Act: -0.1700
Data Index: 3906804 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.8946. Min Act: -0.1700
Data Index: 5720892 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.9258. Min Act: -0.1700
Data Index: 2198246 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.8946. Min Act: -0.1700
Data Index: 2408669 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.8633. Min Act: -0.1700
Data Index: 33011 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.8320. Min Act: -0.1700
Data Index: 3714965 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4884. Min Range: -4.4884
Max Act: 3.8008. Min Act: -0.1700
Data Index: 7394956 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19