Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4795910 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.7091. Min Act: -0.1700
Data Index: 3441129 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.7091. Min Act: -0.1700
Data Index: 4635752 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.6466. Min Act: -0.1700
Data Index: 603507 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.5216. Min Act: -0.1700
Data Index: 3441132 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.5216. Min Act: -0.1700
Data Index: 8239254 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.4904. Min Act: -0.1700
Data Index: 7967471 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.4904. Min Act: -0.1700
Data Index: 6333460 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.4279. Min Act: -0.1700
Data Index: 8756956 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2078192 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.4279. Min Act: -0.1700
Data Index: 2078191 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2786772 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3341. Min Act: -0.1700
Data Index: 2300039 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3654. Min Act: -0.1700
Data Index: 4446679 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3654. Min Act: -0.1700
Data Index: 8029914 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3029. Min Act: -0.1700
Data Index: 4703289 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3341. Min Act: -0.1700
Data Index: 6962802 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.2716. Min Act: -0.1700
Data Index: 1572609 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.3029. Min Act: -0.1700
Data Index: 4555514 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8029. Min Range: -6.8029
Max Act: 6.2716. Min Act: -0.1700
Data Index: 107440 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19