Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.9146. Min Act: -0.1700
Data Index: 2565474 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.6333. Min Act: -0.1700
Data Index: 139231 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.6646. Min Act: -0.1700
Data Index: 3336040 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.5708. Min Act: -0.1700
Data Index: 824823 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.5083. Min Act: -0.1700
Data Index: 5243592 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.5083. Min Act: -0.1700
Data Index: 8488019 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4771. Min Act: -0.1700
Data Index: 7187612 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4458. Min Act: -0.1700
Data Index: 7488967 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4458. Min Act: -0.1700
Data Index: 7228143 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4146. Min Act: -0.1700
Data Index: 5594223 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4146. Min Act: -0.1700
Data Index: 650851 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4146. Min Act: -0.1700
Data Index: 8048372 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4146. Min Act: -0.1700
Data Index: 2404429 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3833. Min Act: -0.1700
Data Index: 5857547 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.4146. Min Act: -0.1700
Data Index: 8420713 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3833. Min Act: -0.1700
Data Index: 914947 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3521. Min Act: -0.1700
Data Index: 4857903 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3521. Min Act: -0.1700
Data Index: 6806439 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3208. Min Act: -0.1700
Data Index: 2878902 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9146. Min Range: -4.9146
Max Act: 4.3833. Min Act: -0.1700
Data Index: 2187562 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19