Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.4043. Min Act: -0.1700
Data Index: 5553567 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.4043. Min Act: -0.1700
Data Index: 5331487 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.3418. Min Act: -0.1700
Data Index: 4870356 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.3106. Min Act: -0.1700
Data Index: 1804342 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.2168. Min Act: -0.1699
Data Index: 5907599 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.2168. Min Act: -0.1700
Data Index: 2896915 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 2488436 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 5480526 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1543. Min Act: -0.1700
Data Index: 5110012 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1543. Min Act: -0.1700
Data Index: 8283499 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1543. Min Act: -0.1700
Data Index: 5158253 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1323750 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1543. Min Act: -0.1700
Data Index: 6796383 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1543. Min Act: -0.1700
Data Index: 5574304 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1337087 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 2468144 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 3220125 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 3308338 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 498427 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1884047 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19