Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1125 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.9749. Min Act: -0.1700
Data Index: 5349899 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.4124. Min Act: -0.1700
Data Index: 7373224 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.3499. Min Act: -0.1700
Data Index: 7440906 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.3499. Min Act: -0.1700
Data Index: 4992791 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.0999. Min Act: -0.1700
Data Index: 7124659 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9749. Min Range: -9.9749
Max Act: 9.0374. Min Act: -0.1700
Data Index: 1348895 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.9124. Min Act: -0.1700
Data Index: 5842014 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.9124. Min Act: -0.1700
Data Index: 2276814 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.8499. Min Act: -0.1700
Data Index: 5196043 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.8499. Min Act: -0.1700
Data Index: 5454710 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.8499. Min Act: -0.1700
Data Index: 5777906 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.8499. Min Act: -0.1700
Data Index: 1130386 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7249. Min Act: -0.1700
Data Index: 5958902 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7874. Min Act: -0.1700
Data Index: 7988549 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7874. Min Act: -0.1700
Data Index: 5335308 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7874. Min Act: -0.1700
Data Index: 8442513 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7874. Min Act: -0.1700
Data Index: 4569175 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7249. Min Act: -0.1700
Data Index: 2062877 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7249. Min Act: -0.1700
Data Index: 5584430 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9749. Min Range: -9.9749
Max Act: 8.7249. Min Act: -0.1700
Data Index: 7588579 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19