Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.2801. Min Act: -0.1700
Data Index: 7876136 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.1863. Min Act: -0.1700
Data Index: 806398 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.1551. Min Act: -0.1700
Data Index: 4980698 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.1238. Min Act: -0.1700
Data Index: 4052167 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.1238. Min Act: -0.1700
Data Index: 2468913 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.1238. Min Act: -0.1700
Data Index: 7387855 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.0926. Min Act: -0.1700
Data Index: 6655256 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.0926. Min Act: -0.1700
Data Index: 7900762 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2801. Min Range: -4.2801
Max Act: 4.0926. Min Act: -0.1700
Data Index: 890987 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9988. Min Act: -0.1700
Data Index: 4385597 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1084981 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9988. Min Act: -0.1700
Data Index: 7012681 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6399422 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1945550 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9363. Min Act: -0.1700
Data Index: 259279 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3603882 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9363. Min Act: -0.1700
Data Index: 3474060 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9050. Min Act: -0.1700
Data Index: 7105309 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9050. Min Act: -0.1700
Data Index: 249760 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2801. Min Range: -4.2801
Max Act: 3.9050. Min Act: -0.1700
Data Index: 1945737 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19